INDEX

Explanations

waste

np_max-act · gemini-2.0-flash

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

tur

-0.29

wheel

-0.28

-wheel

-0.26

reve

-0.26

clo

-0.26

olor

-0.26

etur

-0.25

etr

-0.25

autÃ©

-0.24

twenty

-0.24

POSITIVE LOGITS

å¤įåĲĪ

0.35

erah

0.28

esters

0.28

baugh

0.26

å¤ªå¤§

0.25

reek

0.25

Units

0.25

 Units

0.24

å¤ª

0.24

æ°Ķæ°Ľ

0.24

Activations Density 0.007%

waste

No Comments

No Known Activations