INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

LOPT

-0.27

Mog

-0.25

å¼ĢæĿ¥

-0.25

 Halloween

-0.25

/release

-0.25

locals

-0.24

 ModelState

-0.24

/format

-0.24

æ¡«

-0.24

RELEASE

-0.24

POSITIVE LOGITS

esar

0.31

ãģĸ

0.28

Ã©nÃ©

0.27

å§ĵåĲį

0.26

 lump

0.26

andex

0.24

åįģ

0.23

trail

0.23

åħ³ç¨İ

0.23

 Here

0.23

Activations Density 0.012%

No Known Activations

This feature has no known activations.