INDEX

Explanations

's

np_max-act-logits · gemini-2.0-flash

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

 operation

-0.31

inke

-0.29

xDC

-0.29

defs

-0.28

 allegiance

-0.28

æľĢåĲİä¸Ģæ¬¡

-0.28

 action

-0.27

è¾ĩ

-0.27

operation

-0.27

äºĭä¸ļåıĳå±ķ

-0.27

POSITIVE LOGITS

uated

0.28

 eyes

0.26

 feet

0.25

èĪį

0.25

 elbows

0.24

ury

0.24

 hats

0.24

ungs

0.23

 Eyes

0.23

ambi

0.23

Activations Density 0.002%

's

No Comments

No Known Activations