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

LOGGER

-0.26

aired

-0.26

 motifs

-0.25

å¿ĥæĥ³

-0.24

 resulting

-0.24

 ensuing

-0.24

 unseen

-0.23

éĺħè§Ī

-0.23

 subsequent

-0.23

 studios

-0.23

POSITIVE LOGITS

çļĦè§Ĵèī²

0.33

ä¼ł

0.30

ä¼łéĢĴ

0.30

éģĹ

0.28

 allo

0.27

 regul

0.26

åĲĦè¡Į

0.26

 ÑĢÐ¾Ð»Ð¸

0.25

åĢļ

0.25

çĭŃ

0.25

Activations Density 0.001%

No Known Activations

This feature has no known activations.