© 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 · 41029 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
41029

INDEX

Explanations

ear

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

助推

-0.07

 Attached

-0.07

 poses

-0.07

 가져

-0.07

Elim

-0.07

.getBounds

-0.07

 الغذائي

-0.07

ፖ

-0.07

 التش

-0.07

pieczeń

-0.07

POSITIVE LOGITS

0.07

cron

0.06

年起

0.06

cus

0.06

ᡴ

0.06

 king

0.06

 TreeNode

0.06

莲

0.06

(v

0.06

Specifier

0.06

Activations Density 0.002%

No Known Activations