Visualize and trace the internal reasoning steps of a model with custom prompts, pioneered by Anthropic's circuit tracing papers.
Steer
Modify model behavior by steering its activations using latents or custom vectors. Steering supports instruct (chat) and reasoning models, and has fully customizable temperature, strength, seed, etc.
Search
Search over 50,000,000 latents/vectors, either by semantic similarity to explanation text, or by running custom text via inference through a model to find top matches.
Search via Inference
Run Example Search
API + Libraries
Neuronpedia hosts the world's first interpretability API (March 2024) - and all functionality is available by API or Python/TypeScript libraries. Most endpoints have an OpenAPI spec and interactive docs.
Inspect
Go in depth on each probe/latent/feature with top activations, top logits, activation density, and live inference testing. All dashboards have unique links, can be compiled into sharable lists, and supports IFrame embedding, as demonstrated here.
Who We Are
Neuronpedia was created by Johnny Lin, an ex-Apple engineer who previously founded a privacy startup. Neuronpedia is supported by Decode Research, Open Philanthropy, the Long Term Future Fund, AISTOF, Anthropic, Manifund, and others.