© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 41988 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
41988

INDEX

Explanations

ive

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

Not in Any Lists

No Comments

Negative Logits

חלון

-0.08

RO

-0.07

ipelines

-0.07

Ộ

-0.07

 condemn

-0.07

 expended

-0.07

겹

-0.07

.Evaluate

-0.07

.rf

-0.07

벋

-0.06

POSITIVE LOGITS

*math

0.07

 faith

0.07

 peł

0.07

 DataFrame

0.07

emble

0.07

 McLaren

0.07

 chois

0.07

大全

0.07

描

0.06

 Family

0.06

Activations Density 0.000%

No Known Activations