INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Urban

-0.26

åĲĪæ³ķ

-0.26

 Urban

-0.25

zza

-0.25

 RuntimeException

-0.24

Disposable

-0.24

ently

-0.24

åĽ½æĹĹ

-0.24

Alg

-0.24

 Albert

-0.23

POSITIVE LOGITS

ä¸Ģä¸¾

0.29

çĲĨ

0.28

 pitch

0.25

ç»¼åĲĪæ²»çĲĨ

0.25

 phased

0.24

ä¸Ģç»ı

0.24

ommen

0.24

pitch

0.24

arÄ±

0.24

çĶĺ

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.