INDEX

Explanations

ever

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

med

-0.29

sessionId

-0.27

fi

-0.27

 tens

-0.27

 Consort

-0.25

ìľĦìĽĲíļĮ

-0.25

\xaa

-0.24

ç·£

-0.24

gan

-0.23

 Libre

-0.23

POSITIVE LOGITS

olla

0.30

ITOR

0.25

vided

0.25

 Naked

0.25

 xtype

0.24

æĸĳ

0.23

/Delete

0.23

osex

0.23

çĸ´

0.23

 onDelete

0.23

Activations Density 0.000%

ever

No Comments

No Known Activations