Interpretability

Opening models up: probes, steering and weight-level edits.

All AI news Agents RAG Interpretability Infra

Interpretability · 2 Dec 2025Can you steer sycophancy out of a small model without retraining it?LLM sycophancy, removed with activation steering: it shows up as a linear direction in a small model's hidden states. Subtracting that direction while the model generates raised accuracy on sycophantic prompts from 12.5% to 53.8% on Qwen3-0.6B, with no fine-tuning.

Follow along: RSS feed