© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 89363 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
89363

INDEX

Explanations

:

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

吸附

-0.07

:")

-0.07

 corrective

-0.07

SDL

-0.07

 enjo

-0.07

下巴

-0.07

----

-0.07

"><!--

-0.07

god

-0.07

 ming

-0.07

POSITIVE LOGITS

خصص

0.08

_ALLOW

0.06

Await

0.06

Function

0.06

发生了

0.06

aset

0.06

פור

0.06

ScreenState

0.06

 nowhere

0.06

ประหย

0.06

Activations Density 0.000%

No Known Activations