INDEX

Explanations

menopause

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åıĭ

-0.32

ici

-0.31

æ··

-0.28

 CHUNK

-0.25

 chunk

-0.25

Ware

-0.25

(('

-0.25

æĴķ

-0.25

chunk

-0.25

 Chunk

-0.24

POSITIVE LOGITS

ä¹ı

0.33

 rendered

0.28

resa

0.28

oton

0.27

çĶ¨çĶµ

0.27

ä¸ĩä¸ª

0.26

ç»Ŀå¯¹

0.25

render

0.25

ersh

0.25

èĢĮåĩº

0.25

Activations Density 0.007%

menopause

No Comments

No Known Activations