© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 5683 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
5683

INDEX

Explanations

low

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

冻

-0.08

 maintenance

-0.07

'.$

-0.07

.$

-0.07

𪾢

-0.07

INUE

-0.07

冻结

-0.07

[(

-0.06

 Schneider

-0.06

itle

-0.06

POSITIVE LOGITS

〶

0.09

.depend

0.08

_VOL

0.08

_removed

0.07

Ϲ

0.07

므로

0.07

🥔

0.07

Female

0.07

Off

0.07

alım

0.07

Activations Density 0.001%

No Known Activations