INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

ViewSet

-0.27

å¸Ĥåľºç«ŀäºī

-0.26

æ½ľ

-0.26

ç«ŀæĬĢ

-0.26

dy

-0.26

 advanced

-0.25

é¹ľ

-0.25

à¹Īà¸ĩ

-0.25

éĽ·æĸ¯

-0.24

ç»ĵ

-0.24

POSITIVE LOGITS

 afterward

0.29

xFE

0.27

_formats

0.26

Formats

0.25

åıªæĺ¯

0.24

éģĲ

0.24

å¢ŀéĩı

0.24

rades

0.24

 skype

0.24

 âĪĢ

0.24

Activations Density 0.039%

No Comments

No Known Activations