© 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 · 41698 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
41698

INDEX

Explanations

things

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

egan

-0.07

bove

-0.07

 книг

-0.07

ToProps

-0.07

绗

-0.07

하지

-0.07

 legends

-0.07

 depths

-0.07

 predecessors

-0.06

 spar

-0.06

POSITIVE LOGITS

ǎ

0.07

是指

0.07

(HttpServletRequest

0.07

lastic

0.07

Film

0.07

-Free

0.07

 najczę

0.06

dns

0.06

まって

0.06

江西省

0.06

Activations Density 0.031%

No Known Activations