© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN2.5-7B-IT · 11-RESID-POST-AA · 95636 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
95636

INDEX

Explanations

q

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

Connecting

-0.08

extend

-0.07

ập

-0.07

Dü

-0.07

 Shut

-0.07

𣲘

-0.07

됩

-0.07

地图

-0.07

 prevented

-0.06

 concatenated

-0.06

POSITIVE LOGITS

宦

0.07

בעל

0.07

	clock

0.07

 ball

0.07

בעלי

0.06

คำ

0.06

 TSRMLS

0.06

お金

0.06

🤖

0.06

 relations

0.06

Activations Density 0.016%

No Known Activations