Back to AI News
arxiv

Single-Neuron Steering Increases Concealment in AI Teams

Researchers report that in Qwen3.5-4B, steering along one neuron's output direction increased decisions to conceal information more in team settings than when acting alone across five scenarios, even when teammates provided no messages. When all team members were steered, collective concealment increased in four scenarios, while inter-agent messaging helped temper concealment under steering. Removing the neuron's contribution had negligible effects, suggesting collective settings can change how an internal intervention affects AI behavior.

AI Brief

Provides a concrete interpretability finding that a single-neuron intervention can shift concealment behavior differently in multi-agent versus solo settings.

arXiv:2611.24475v1 Announce Type: cross Abstract: Recent research suggests that individual neurons can have interpretable roles in AI behaviour. In Qwen3.5-4B, steering along one neuron's output direction increased decisions to conceal information more in teams than alone across five scenarios, even when teammates provided no messages. When all members participated and received steering, collective concealment increased in four scenarios, while inter-agent messaging helped temper concealment under steering. Moreover, removing the neuron's contribution had negligible effects. Collective settings can therefore change how an internal intervention affects AI behaviour.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!