© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 68641 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
68641

INDEX

Explanations

ographic

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

Not in Any Lists

No Comments

Negative Logits

ình

-0.08

wz

-0.08

 jako

-0.07

ũ

-0.07

 adopt

-0.07

nam

-0.07

育

-0.07

 hast

-0.06

솟

-0.06

cmp

-0.06

POSITIVE LOGITS

bery

0.07

.iOS

0.07

 Wheeler

0.07

.getAction

0.07

 Forms

0.07

 userInput

0.06

<button

0.06

ترك

0.06

 PUBLIC

0.06

 français

0.06

Activations Density 0.001%

No Known Activations