© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 120969 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
120969

INDEX

Explanations

legal documents

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

AAD

-0.07

균

-0.07

הג

-0.07

feat

-0.07

 screamed

-0.07

 kein

-0.07

.Tick

-0.07

Need

-0.06

癀

-0.06

Exclude

-0.06

POSITIVE LOGITS

 During

0.07

 Wife

0.07

晚上

0.07

歌舞

0.07

 Mont

0.06

 Multip

0.06

 UIButton

0.06

字

0.06

fontSize

0.06

 PRES

0.06

Activations Density 0.006%

No Known Activations