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

 Platt

-0.29

å·¨

-0.29

Kl

-0.28

antly

-0.28

Lay

-0.28

åĮħ

-0.26

CL

-0.25

 instead

-0.25

Presentation

-0.24

instead

-0.24

POSITIVE LOGITS

è¿Ļä¸ªäºº

0.26

Ã´i

0.25

vac

0.25

çļĦæł·åŃĲ

0.25

 cush

0.24

è¡Įäºĭ

0.24

<WebElement

0.24

 fellow

0.24

assin

0.24

ouch

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.