INDEX

Explanations

Forms of "to be"

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

kins

-0.27

mel

-0.27

usp

-0.26

vor

-0.26

 prefixed

-0.25

 homo

-0.25

ç§°

-0.25

ä¼¼

-0.25

mel

-0.25

uds

-0.24

POSITIVE LOGITS

è¿Ļåıªæĺ¯

0.33

åıªæĺ¯ä¸Ģä¸ª

0.31

ä¸įè¶³ä»¥

0.31

æ¯ķç«Łæĺ¯

0.29

ä¸įå®Į

0.28

ystate

0.28

 nonetheless

0.28

ioc

0.27

ä¸įè¶³

0.27

eneric

0.27

Activations Density 0.004%

Forms of "to be"

No Comments

No Known Activations