© 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 · 76516 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
76516

INDEX

Explanations

No Explanations Found

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

_deinit

-0.08

.O

-0.07

Minnesota

-0.07

.*↵

-0.07

 Examiner

-0.07

	contentPane

-0.07

🐯

-0.06

 examined

-0.06

ROS

-0.06

 Heat

-0.06

POSITIVE LOGITS

uben

0.07

﹃

0.07

 Klaus

0.07

ourney

0.07

(shader

0.06

وفق

0.06

哼

0.06

Jub

0.06

安全

0.06

пов

0.06

Activations Density 0.024%

No Known Activations