© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 40625 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
40625

INDEX

Explanations

L

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

トラ

-0.07

_SECURE

-0.07

nds

-0.07

둬

-0.07

 Bermuda

-0.07

-ext

-0.07

甜甜

-0.07

_uid

-0.07

-period

-0.07

 würde

-0.06

POSITIVE LOGITS

 digit

0.07

OFF

0.07

 Subjects

0.06

twór

0.06

 münchen

0.06

ay

0.06

ijo

0.06

ach

0.06

toe

0.06

反过来

0.06

Activations Density 0.002%

No Known Activations