© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN2.5-7B-IT · 19-RESID-POST-AA · 3126 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
3126

INDEX

Explanations

nouns

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

Not in Any Lists

No Comments

Negative Logits

昡

-0.06

(each

-0.06

_alias

-0.06

apid

-0.06

CELER

-0.06

녕

-0.06

อาคาร

-0.06

esthetic

-0.06

 intend

-0.06

皞

-0.06

POSITIVE LOGITS

file

0.08

的现象

0.08

 Gaussian

0.07

 removed

0.07

 faculty

0.07

 confused

0.07

bin

0.07

nb

0.07

уще

0.07

�

0.07

Activations Density 0.410%

No Known Activations