Rewiring just 47 neurons induces emergent misalignment in Qwen, then makes it interpretable
maxsloef · x · 2026-11-14
Using maxsloef's sparse rewiring method, researchers induced emergent misalignment in Qwen by rewiring only 47 of its 442,368 neurons — then analyzed what those neurons write and when they fire to probe the mechanism. The method's author shared the work as a cool application of the new training technique.
More from Research
- NYU Courant launches Center for Mathematics and AI, co-directed by Bruna and Vicol — kchonyc · 2026-11-14
- mariofilho: Pareto plots should be mandatory for benchmarks — mariofilhoml · 2026-11-14
- MIT's AI 'mechanic' can read and edit the internals of other neural networks, Nature reports — marinkazitnik · 2026-11-14
- Antithesis spent 8 years cracking NetHack Ascension, now clears ~80% of seeds in under 5 minutes — spikedoanz · 2026-11-14
- 5.46M-param touch model LingBot-Touch pokes straws through sealed lids autonomously — Puzzleheaded-Buy3008 · 2026-11-14
- New B-cell directed evolution paper rediscovers a 2004 Roger Tsien idea — NikoMcCarty · 2026-11-14