© 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 · 80735 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
80735

INDEX

Explanations

wings

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

殺

-0.07

⟫

-0.07

שוקולד

-0.06

-0.06

$json

-0.06

⼒

-0.06

ería

-0.06

_End

-0.06

 undone

-0.06

ikut

-0.06

POSITIVE LOGITS

帑

0.08

毋

0.07

槟

0.07

pci

0.07

NU

0.07

民主生活

0.07

 domination

0.07

TemplateName

0.07

 McCart

0.07

 Legislature

0.07

Activations Density 0.006%

No Known Activations