© 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 · 45406 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
45406

INDEX

Explanations

dissent

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

 TRUE

-0.07

 envi

-0.07

.ro

-0.07

 Univ

-0.07

 masterpiece

-0.07

 setId

-0.07

Pic

-0.07

alphabet

-0.07

Inst

-0.06

 startPos

-0.06

POSITIVE LOGITS

 fasting

0.07

}):

0.07

 baker

0.07

сан

0.07

 уме

0.07

쉔

0.07

 Buchanan

0.06

섰

0.06

医生

0.06

ดาร

0.06

Activations Density 0.002%

No Known Activations