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

_timing

-0.30

tant

-0.30

uary

-0.28

keit

-0.27

spiel

-0.27

tings

-0.26

Ã©tique

-0.26

ä¹łæĥ¯

-0.25

sburg

-0.25

ery

-0.25

POSITIVE LOGITS

 concluded

0.27

 disap

0.26

Lua

0.26

/il

0.25

 concludes

0.24

ç»ĵ

0.23

 diplom

0.23

 conclusion

0.23

neg

0.23

 Conclusion

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.