© 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 · 11215 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
11215

INDEX

Explanations

reference

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

 Ting

-0.07

 liner

-0.07

툽

-0.07

𝐩

-0.07

fluid

-0.07

니

-0.06

くる

-0.06

 wildly

-0.06

UG

-0.06

fore

-0.06

POSITIVE LOGITS

٫

0.08

orama

0.07

de

0.07

 probabil

0.07

 quận

0.07

 foram

0.07

camera

0.06

 ENTITY

0.06

Ra

0.06

_Char

0.06

Activations Density 0.004%

No Known Activations