© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 58911 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
58911

INDEX

Explanations

Bantam

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

均使其

-0.08

Ted

-0.07

לשון

-0.07

-0.07

IFA

-0.07

宿迁

-0.07

슥

-0.07

 prisoner

-0.07

traî

-0.07

Domain

-0.07

POSITIVE LOGITS

ça

0.07

ក

0.07

꺄

0.07

_articles

0.07

nth

0.07

 скач

0.06

ἅ

0.06

forall

0.06

SCT

0.06

 descriptors

0.06

Activations Density 0.001%

No Known Activations