© 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 · 9216 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
9216

INDEX

Explanations

moments of realization

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

 Од

-0.06

':[

-0.06

خل

-0.06

Tue

-0.06

fal

-0.06

 Seems

-0.06

 Chambers

-0.06

 plurality

-0.06

	count

-0.06

 дух

-0.06

POSITIVE LOGITS

js

0.07

 inspector

0.07

respuesta

0.07

华润

0.07

كس

0.07

writer

0.07

0.06

حرك

0.06

𬮱

0.06

ង

0.06

Activations Density 0.066%

No Known Activations