https://liqq010.github.io/tags/interpretability/ Recent content in Interpretability on liqq Hugo en-us Wed, 04 Nov 2026 00:00:00 +0000 https://liqq010.github.io/posts/weight-space-programming-qwen-loops/ Wed, 04 Nov 2026 00:00:00 +0000 https://liqq010.github.io/posts/weight-space-programming-qwen-loops/ How an LLM edited 0.016% of Qwen3.5-0.8B’s weights to break its reasoning loops: directional ablation from the refusal-direction work, then pushed further with a strength α and 64 selected neurons per layer.