© 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 · 19-RESID-POST-AA · 48816 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
48816

INDEX

Explanations

"to be"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

autorelease

-0.07

SGlobal

-0.07

它们

-0.07

 Chung

-0.07

ifique

-0.07

Participant

-0.07

もち

-0.06

 Unreal

-0.06

UILD

-0.06

ฝน

-0.06

POSITIVE LOGITS

⌯

0.07

-api

0.07

>>

0.07

荞

0.06

采纳

0.06

璇

0.06

 impressed

0.06

-direction

0.06

0.06

-fired

0.06

Activations Density 0.162%

No Known Activations