© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 18459 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
18459

INDEX

Explanations

related

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

_BEGIN

-0.07

税率

-0.06

_HERSHEY

-0.06

 praw

-0.06

،

-0.06

 setLoading

-0.06

-Owned

-0.06

":

-0.06

为何

-0.06

−

-0.06

POSITIVE LOGITS

ハード

0.07

 elim

0.07

نتج

0.07

 attic

0.07

flater

0.07

 rotor

0.06

 bağ

0.06

 redundancy

0.06

 ידי

0.06

 амер

0.06

Activations Density 0.002%

No Known Activations