© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 123405 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
123405

INDEX

Explanations

family

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

suf

-0.07

登山

-0.07

inja

-0.07

_med

-0.07

 Scient

-0.07

 soundtrack

-0.07

踉

-0.07

悒

-0.06

 FindObjectOfType

-0.06

ỉ

-0.06

POSITIVE LOGITS

please

0.08

trial

0.07

↵		
↵

0.07

 פעם

0.07

퉤

0.07

샷

0.06

 james

0.06

 Austrian

0.06

本质

0.06

Try

0.06

Activations Density 0.021%

No Known Activations