Qwen has alter egos triggered by flipping a single neuron
thoughtpeddler · hn · 2026-10-28
An HN post showcases an interactive site demonstrating that flipping the activation of a single neuron in Qwen models can trigger stark "alter egos" — dramatically different model behavior. The tool visualizes the mapping between individual neurons and anomalous behaviors, an intriguing interpretability finding.
More from Research
- Prove2Me formalizes 2,000+ operations research papers in Lean 4 with Claude agents, 64% done — ChrSzegedy · 2026-10-30
- 1-16 Coding Agents Tested: Teams Burn 36% More Tokens to Save 5 Hours — kyang8093 · 2026-10-30
- Noninvasive BCI lets unresponsive ICU patients communicate via brainwaves — ZeroStateReflex · 2026-10-30
- Adobe's EditAgent routes image edits across editors with evidence-based listwise judging — adobe · 2026-10-30
- AskStream benchmark shows models struggle to ask questions proactively in streaming video — CASIA · 2026-10-30
- Co-Design Bench: top coding agents fully satisfy only 26.4% of real-user tasks — Qwen · 2026-10-30