arxiv
PublishedSeptember 15, 2026 at 4:00 AM
—neutral
Signatures of Steerability in Activation Space of Language Models
Publisher summary· verbatim
arXiv:2609.14151v1 Announce Type: cross Abstract: Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model behavior. Despite this success in controlling certain model behaviors, the effectiveness of activation
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
The Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗