© 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 · 20870 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
20870

INDEX

Explanations

remain

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

升华

-0.08

.upper

-0.07

וצר

-0.07

拱

-0.07

Cls

-0.07

iii

-0.07

 inorder

-0.07

 juegos

-0.07

getPosition

-0.07

탑

-0.07

POSITIVE LOGITS

텦

0.08

 remained

0.07

Ma

0.07

.day

0.07

Mich

0.07

Yak

0.06

chem

0.06

 Went

0.06

dat

0.06

 been

0.06

Activations Density 0.031%

No Known Activations