cd /news/large-language-models/tracing-causal-structure-in-llm-gene… · home topics large-language-models article
[ARTICLE · art-65615] src=lesswrong.com ↗ pub= topic=large-language-models verified=true sentiment=· neutral

Tracing causal structure in LLM-generated text: a different lens on the Dallas circuit

A new approach to mechanistic interpretability traces causal structure in LLM-generated text rather than internal activations, producing attribution graphs that resemble reasoning trajectories. The method, applied to Qwen3-1.7B using gradient attribution and sparse pruning, requires almost no semantic knowledge and could help study information propagation during inference.

read1 min views5 publishedJul 20, 2026

The classic "Dallas" example from Anthropic focuses on an internal circuit in an LLM.

I became curious about what the same underlying process looks like when viewed through the **generated reasoning trace **instead of hidden activations. The resulting attribution graph looks much more structured than I expected:

Below is an animated version:

Using simple gradient attribution, DAG tracing, and sparse pruning on Qwen3-1.7B, the resulting graph already resembles a 'reasoning trajectory'. This feels like a different perspective on mechanistic interpretability: instead of analyzing internal circuits directly, it explores causal structure within the generated language itself through context-attribution DAGs. P.S. There is some related work, such as the Thought Anchors series. However, the goals are different, and their approach relies on prior semantic knowledge, whereas this approach requires almost no semantic knowledge.

I'm curious whether this perspective can become useful beyond visualization—for example, as a way to study how information propagates through language during inference, and perhaps, more broadly, the informational dynamics of language and LLMs.

Source code: https://github.com/dqy08/InfoLens

── more in #large-language-models 4 stories · sorted by recency
── more on @anthropic 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/tracing-causal-struc…] indexed:0 read:1min 2026-07-20 ·