INDEX

Explanations

"with" in conversational text

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

 Evening

-0.30

 Nacht

-0.28

 evening

-0.27

æ´»è·ĥ

-0.26

dag

-0.25

ÑĤÐ¸ÑĢ

-0.25

èŀįåĮĸ

-0.25

 decltype

-0.24

 shredded

-0.24

pi

-0.24

POSITIVE LOGITS

 cree

0.30

èĢĥå¯Ł

0.27

cade

0.27

.weixin

0.25

èĢĥ

0.25

ajor

0.25

ä¸Ģç·Ĵãģ«

0.25

åįĬä¸ª

0.25

 Ð¿ÑĢÐ¾Ð²ÐµÐ´ÐµÐ½

0.24

lemn

0.24

Activations Density 0.003%

"with" in conversational text

No Comments

No Known Activations