INDEX

Explanations

av

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

airy

-0.30

åŀĤçĽ´

-0.29

afen

-0.28

bl

-0.28

ban

-0.28

bag

-0.27

ç¼©å°ı

-0.26

glo

-0.26

æī©å¤§

-0.26

POSITIVE LOGITS

 mach

0.29

edBy

0.29

 thÃ´i

0.27

wdx

0.26

evin

0.26

USED

0.25

ä»»ä½ķæĹ¶åĢĻ

0.25

æ¥¼ä¸ĭ

0.25

æµĵåº¦

0.25

åĪĳäºĭæ¡Īä»¶

0.25

Activations Density 0.008%

av

No Comments

No Known Activations