© 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 · 83438 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
83438

INDEX

Explanations

period

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

 Breast

-0.08

 communicated

-0.08

ignored

-0.07

-0.07

 Community

-0.07

 Drugs

-0.07

-0.07

nicas

-0.07

IFS

-0.07

 fleeing

-0.07

POSITIVE LOGITS

锜

0.07

bounds

0.07

アジ

0.07

奥斯卡

0.07

畢

0.07

냅

0.07

 Lumpur

0.07

�

0.06

ưỡ

0.06

({},

0.06

Activations Density 0.002%

No Known Activations