© 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 · 7-RESID-POST-AA · 76185 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
76185

INDEX

Explanations

ans

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

!',↵

-0.07

 savings

-0.07

leasing

-0.06

옙

-0.06

㌘

-0.06

婆婆

-0.06

﹗

-0.06

צפייה

-0.06

媽媽

-0.06

 movies

-0.06

POSITIVE LOGITS

ينة

0.08

 Nội

0.07

=X

0.07

 Indigenous

0.07

 weiß

0.07

 Jacques

0.07

_COUNT

0.07

 absol

0.06

0.06

섬

0.06

Activations Density 0.002%

No Known Activations