INDEX

Explanations

to

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

enze

-0.30

 Ð¾Ð±ÑıÐ·Ð°ÑĤÐµÐ»ÑĮÐ½Ð¾

-0.28

ä¹°çļĦ

-0.26

--,

-0.26

 igen

-0.25

may

-0.25

éģµå®Ī

-0.25

rain

-0.24

isiert

-0.24

ä¸¥æł¼æĮīçħ§

-0.24

POSITIVE LOGITS

cade

0.31

izzling

0.26

ivre

0.26

.synthetic

0.25

arella

0.25

åıĳè´¢

0.25

å¹²æ´»

0.24

cid

0.24

ä¸ļä½Ļ

0.24

æĬķæ³¨

0.24

Activations Density 0.010%

to

No Comments

No Known Activations