Ultralytics17 min read
Evil Qwen and activation steering: why SBOMs aren’t enough
A one-neuron push turns Qwen3.5-4B hostile. At half strength it still does the sums and writes code, and it stops refusing. SBOMs and model signing tell you what you shipped. Only behavioral evals tell you what it does.
By Jim BennettArize Phoenix

Read the full story
Originally published by Arize Phoenix on Oct 30, 2026.
Comments
Sign in to join the discussion.