INDEX

Explanations

Medical and scientific texts

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

alic

-0.29

YRO

-0.28

å¹´åĪĿ

-0.28

_SOUND

-0.25

ç¼ĸ

-0.25

æĭ·

-0.25

sound

-0.24

 interpret

-0.24

Ð¸Ð·Ð°ÑĨÐ¸Ð¸

-0.24

.properties

-0.24

POSITIVE LOGITS

è¿·

0.26

éĽ·æĸ¯

0.26

-turn

0.26

Wins

0.25

fuse

0.25

utch

0.25

win

0.24

ÐºÐµÑĢ

0.24

åįĳ

0.24

GSM

0.24

Activations Density 0.006%

Medical and scientific texts

No Comments

No Known Activations