© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 75933 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
75933

INDEX

Explanations

weight

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

 geleceği

-0.08

 guerra

-0.08

률

-0.07

elfare

-0.07

fie

-0.07

 Christie

-0.06

�

-0.06

تبادل

-0.06

 imperfect

-0.06

暹

-0.06

POSITIVE LOGITS

 cloak

0.07

Caught

0.07

发

0.07

Girl

0.07

ca

0.07

.StringVar

0.07

HA

0.07

/ag

0.07

pou

0.07

.findViewById

0.07

Activations Density 0.003%

No Known Activations