{"slug": "lenslapse-in-browser-logit-lens-for-interactive-exploration-of-language-model", "title": "LensLapse: In-Browser Logit Lens for Interactive Exploration of Language Model Training Dynamics", "summary": "Tatsuki Okada, Yusuke Sakai and Taro Watanabe presented LensLapse, an MIT-licensed open-source web application that lets users scrub a slider across public checkpoints from five model families and three multilingual checkpoint suites to watch per-layer, per-position logit lens predictions shift from frequency bias to factual knowledge. For browser-compatible models, arbitrary user prompts are probed live in the browser via local inference over per-checkpoint model pairs, with no server, API key or hosting cost, and prompts never leaving the user's device. A single pip install lets users launch the application locally to explore their own models and checkpoints; the paper appears in the AACL-IJCNLP 2026 System Demonstrations proceedings, pages 66–73, and the tool is hosted at iamtatsuki05.github.io/lenslapse.", "body_md": "##### Abstract\n\nThe logit lens is a standard mechanistic interpretability tool for inspecting a Transformer’s predictions across layers. However, existing logit lens tools typically focus on individual checkpoints rather than interactive exploration of a model’s *training history*.\nIn this study, we introduce **LensLapse**, an open-source web application for interactive exploration of a model’s training history through token-level interpretability. Users can scrub a slider across public checkpoints from five model families and three multilingual checkpoint suites and observe how per-layer, per-position logit lens predictions evolve from frequency bias to factual knowledge.\n\nFor browser-compatible models, arbitrary user prompts are probed *live in the browser* via local inference over per-checkpoint model pairs. No server, no API key, no hosting cost, and prompts never leave the user’s device.\n\nMoreover, **LensLapse** supports local models. A single ‘pip install‘ enables users to launch the application and explore their own models and training checkpoints without any additional web setup.\n\nLensLapse is MIT-licensed and permanently hosted at iamtatsuki05.github.io/lenslapse.\n\n- GitHub: https://github.com/iamtatsuki05/lenslapse - PyPI: https://pypi.org/project/lenslapse/ - docs: https://iamtatsuki05.github.io/lenslapse/docs/ - YouTube: https://youtu.be/OBnvG9Ru3j8\n\n- Anthology ID:\n- 2026.aacl-demo.9\n- Volume:\n- [Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations](https://aclanthology.org/volumes/2026.aacl-demo/)\n- Month:\n- November\n- Year:\n- 2026\n- Address:\n- Hengqin, China\n- Editors:\n- [Ningyu Zhang](https://aclanthology.org/people/ningyu-zhang/) ,[Derry Wijaya](https://aclanthology.org/people/derry-tanti-wijaya/)\n- Venues:\n- [AACL](https://aclanthology.org/venues/aacl/) |[IJCNLP](https://aclanthology.org/venues/ijcnlp/)\n- SIG:\n- Publisher:\n- Association for Computational Linguistics\n- Note:\n- Pages:\n- 66–73\n- Language:\n- URL:\n- [https://aclanthology.org/2026.aacl-demo.9/](https://aclanthology.org/2026.aacl-demo.9/)\n- DOI:\n- Cite (ACL):\n- Tatsuki Okada, Yusuke Sakai, and Taro Watanabe. 2026. [LensLapse: In-Browser Logit Lens for Interactive Exploration of Language Model Training Dynamics](https://aclanthology.org/2026.aacl-demo.9/) . In*Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations* , pages 66–73, Hengqin, China. Association for Computational Linguistics.\n- Cite (Informal):\n- [LensLapse: In-Browser Logit Lens for Interactive Exploration of Language Model Training Dynamics](https://aclanthology.org/2026.aacl-demo.9/) (Okada et al., AACL-IJCNLP 2026)\n- PDF:\n- [https://aclanthology.org/2026.aacl-demo.9.pdf](https://aclanthology.org/2026.aacl-demo.9.pdf)", "url": "https://wpnews.pro/news/lenslapse-in-browser-logit-lens-for-interactive-exploration-of-language-model", "canonical_source": "https://aclanthology.org/2026.aacl-demo.9/", "published_at": "2026-11-02 00:00:00+00:00", "updated_at": "2026-11-05 02:19:46.297294+00:00", "lang": "en", "topics": ["ai-research", "large-language-models", "ai-tools", "developer-tools", "machine-learning"], "entities": ["LensLapse", "Tatsuki Okada", "Yusuke Sakai", "Taro Watanabe", "Association for Computational Linguistics", "AACL-IJCNLP 2026", "GitHub", "PyPI"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/lenslapse-in-browser-logit-lens-for-interactive-exploration-of-language-model", "markdown": "https://wpnews.pro/news/lenslapse-in-browser-logit-lens-for-interactive-exploration-of-language-model.md", "text": "https://wpnews.pro/news/lenslapse-in-browser-logit-lens-for-interactive-exploration-of-language-model.txt", "jsonld": "https://wpnews.pro/news/lenslapse-in-browser-logit-lens-for-interactive-exploration-of-language-model.jsonld"}}