© 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 · 24597 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
24597

INDEX

Explanations

Game card descriptions

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

.COMP

-0.07

การ

-0.07

�

-0.07

_percent

-0.07

 guar

-0.07

xmin

-0.07

_palette

-0.07

anism

-0.07

 cooper

-0.07

 رئيس

-0.07

POSITIVE LOGITS

ענה

0.07

ゕ

0.07

 ]
↵

0.07

 blocking

0.07

_PRINT

0.07

far

0.07

 dhcp

0.07

ظاهرة

0.07

",

0.07

قيقة

0.07

Activations Density 0.014%

No Known Activations