© 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 · 109588 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
109588

INDEX

Explanations

SEC

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

nome

-0.08

anax

-0.07

TextNode

-0.07

(nome

-0.07

plug

-0.07

单品

-0.07

穹

-0.07

phoneNumber

-0.07

쳄

-0.07

👾

-0.06

POSITIVE LOGITS

 consolidated

0.07

指示

0.07

 우리는

0.07

 verifies

0.07

holes

0.07

ulture

0.07

LO

0.07

 recount

0.07

 nước

0.07

�

0.06

Activations Density 0.004%

No Known Activations