INDEX

Explanations

instrument

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

OTTOM

-0.26

Ã¤ter

-0.25

åı¦ä¸ĢåįĬ

-0.25

-volume

-0.24

ather

-0.24

agrams

-0.24

kÄ±

-0.24

 KÃ¶nig

-0.24

-collar

-0.24

 Dictionary

-0.24

POSITIVE LOGITS

vic

0.29

Öģ

0.28

vic

0.28

 faculties

0.28

Imp

0.27

ëĭ¤ê°Ģ

0.26

èĮ±

0.26

icy

0.25

aea

0.25

ero

0.25

Activations Density 0.005%

instrument

No Comments

No Known Activations