© 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 · 59321 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
59321

INDEX

Explanations

vine

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

ersist

-0.08

erspective

-0.07

 Picks

-0.07

 Ground

-0.07

 Nick

-0.06

Nit

-0.06

culate

-0.06

 Pang

-0.06

 Dependencies

-0.06

 Dick

-0.06

POSITIVE LOGITS

쑥

0.07

 ślub

0.07

されます

0.07

.gf

0.07

.slide

0.07

上报

0.07

 INVALID

0.07

食欲

0.06

픙

0.06

如今

0.06

Activations Density 0.002%

No Known Activations