LLM introspection: Qwen3 can detect and report injected attention, experiments show

Sauers_ · x · 2026-11-19

Interpretability researcher Sauers ran experiments testing whether LLMs can introspect on and metacognitively control their attention.

The author concludes the model has privileged introspective access to its own attention. Code is on GitHub.

Related event: Experiments suggest Qwen3-32B has privileged introspective access to its own attention(10 posts)→

Original post →

More from Models

Models channel →