© 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 · 15-RESID-POST-AA · 28469 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
28469

INDEX

Explanations

Lawrence

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

志愿服务

-0.07

xBC

-0.07

ElementException

-0.07

 volunteer

-0.07

**

-0.07

MLP

-0.06

xAC

-0.06

 inspire

-0.06

🎸

-0.06

镴

-0.06

POSITIVE LOGITS

arguments

0.07

思う

0.07

 twenty

0.07

 There

0.07

 Couldn

0.07

든지

0.07

否定

0.07

Changes

0.07

 compareTo

0.07

雍

0.07

Activations Density 0.003%

No Known Activations