© 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 · 15-RESID-POST-AA · 112941 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
112941

INDEX

Explanations

PL

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

 יודע

-0.08

 Müller

-0.08

ide

-0.07

狡

-0.07

 tank

-0.07

'('

-0.07

 choc

-0.07

 options

-0.07

 השלישי

-0.07

 האחרונים

-0.07

POSITIVE LOGITS

ronic

0.08

黑

0.08

tribution

0.07

minimal

0.07

量子

0.07

SOEVER

0.07

MakeRange

0.07

FL

0.07

_direct

0.07

BI

0.07

Activations Density 0.017%

No Known Activations