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

æ¯ĶåĪ©

-0.26

cul

-0.26

ä¸Ĭæ¦ľ

-0.26

 deprived

-0.26

vers

-0.26

 Swal

-0.25

ect

-0.25

åĵºä¹³

-0.24

è¤«

-0.24

rades

-0.24

POSITIVE LOGITS

 RETURNS

0.30

æķĽ

0.28

 Plates

0.28

 Parallel

0.26

 methods

0.26

@return

0.25

 Plate

0.24

 Ãĸz

0.24

 forks

0.24

 interchangeable

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.