© 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 · 7-RESID-POST-AA · 12336 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
12336

INDEX

Explanations

prepositions

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

Jud

-0.07

 tanks

-0.07

 cylinders

-0.07

 closely

-0.07

-hand

-0.07

DAN

-0.07

Kansas

-0.07

满脸

-0.07

 unidad

-0.07

集中

-0.07

POSITIVE LOGITS

 expectedResult

0.08

𠙶

0.07

 geometric

0.07

 istediğiniz

0.07

郃

0.06

 erhalten

0.06

◴

0.06

 mặt

0.06

ﯣ

0.06

 verschiedenen

0.06

Activations Density 0.974%

No Known Activations