© 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 · 7-RESID-POST-AA · 80855 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
80855

INDEX

Explanations

class

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

 MEMBER

-0.07

 homeland

-0.06

.Listen

-0.06

QUENCY

-0.06

 kullandı

-0.06

馌

-0.06

 PURE

-0.06

鳎

-0.06

axes

-0.06

 Rider

-0.06

POSITIVE LOGITS

 ejemplo

0.07

 thems

0.07

.which

0.07

.userService

0.06

 chem

0.06

 Guill

0.06

楼上

0.06

 Harry

0.06

?>
↵
↵

0.06

There

0.06

Activations Density 0.010%

No Known Activations