© 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 · 11-RESID-POST-AA · 23450 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
23450

INDEX

Explanations

block

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

Blank

-0.07

年薪

-0.07

ReturnValue

-0.07

נסי

-0.07

ߦ

-0.07

 accomplish

-0.07

齉

-0.06

.tm

-0.06

 Benchmark

-0.06

ổ

-0.06

POSITIVE LOGITS

 Module

0.07

 devastated

0.07

IRA

0.07

 jako

0.07

 theoretical

0.06

'"'

0.06

 указан

0.06

做法

0.06

дут

0.06

 spike

0.06

Activations Density 0.003%

No Known Activations