© 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 · 45034 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
45034

INDEX

Explanations

code snippets

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

 lever

-0.08

셔

-0.07

/nav

-0.07

傢

-0.07

 entwick

-0.06

笃

-0.06

 sollte

-0.06

VER

-0.06

leitung

-0.06

 ever

-0.06

POSITIVE LOGITS

rising

0.08

 jsonString

0.08

 половин

0.07

 puzzles

0.07

 differing

0.07

.UndefOr

0.07

rise

0.07

蓇

0.07

楼梯

0.07

)}.

0.07

Activations Density 0.082%

No Known Activations