© 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 · 60043 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
60043

INDEX

Explanations

Metadata extraction

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

 ViewModel

-0.07

 זו

-0.07

gg

-0.07

 عن

-0.07

DataMember

-0.06

atrigesimal

-0.06

_Common

-0.06

gment

-0.06

Destroy

-0.06

(([

-0.06

POSITIVE LOGITS

 labs

0.07

`↵↵

0.07

 Films

0.06

 Trustees

0.06

wis

0.06

arte

0.06

름

0.06

zap

0.06

住在

0.06

 בסדר

0.06

Activations Density 0.035%

No Known Activations