INDEX

Explanations

of

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é½Ĳ

-0.30

voy

-0.28

æł¼å°Ķ

-0.27

ç³ĸå°¿

-0.26

afia

-0.26

çĿĢä»ĸ

-0.25

éĢ»è¾ĳ

-0.25

æ¿ł

-0.25

é½Ĭ

-0.25

 Ð¶ÑĥÑĢÐ½Ð°Ð»

-0.25

POSITIVE LOGITS

sha

0.26

ccp

0.25

ä¸Ĭå®ĺ

0.25

acz

0.25

ochen

0.25

Ngo

0.24

 Ther

0.24

LLC

0.24

 Undert

0.24

eed

0.23

Activations Density 0.013%

of

No Comments

No Known Activations