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

dess

-0.27

 Contributors

-0.26

çŃīå¥ĸ

-0.25

 Govern

-0.24

 Achievement

-0.24

åıªè¦ģæľī

-0.24

RowIndex

-0.24

 Belgi

-0.23

åıªè¦ģ

-0.23

å¦ĤæŀľæĤ¨

-0.23

POSITIVE LOGITS

é©¬æĭī

0.30

forced

0.27

ooting

0.26

è¿ĩ

0.26

æĪĳæĥ³

0.24

çī¹èī²çļĦ

0.24

CAA

0.24

åĽ¾ä¸º

0.24

åį¿

0.24

 exploded

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.