© 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 · 29440 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
29440

INDEX

Explanations

Returned

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

qty

-0.09

(';

-0.08

/site

-0.08

 charset

-0.07

脆

-0.07

 Create

-0.07

addock

-0.07

clean

-0.07

 weak

-0.07

 Read

-0.07

POSITIVE LOGITS

个工作

0.07

 Torah

0.07

Ỹ

0.07

ቅ

0.07

 הפר

0.06

 המש

0.06

NotBlank

0.06

 emple

0.06

משל

0.06

 Echo

0.06

Activations Density 0.025%

No Known Activations