INDEX

Explanations

it

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

icos

-0.28

umbo

-0.26

apo

-0.26

-separated

-0.26

 customers

-0.25

tributes

-0.25

Customers

-0.25

alogy

-0.25

ione

-0.25

åľĨæ»¡å®ĮæĪĲ

-0.25

POSITIVE LOGITS

 giÃ¡o

0.32

-learning

0.31

 learning

0.29

åŃ¦ä¹ł

0.28

è¿Ľä¿®

0.27

fit

0.27

 Ã¶ÄŁret

0.27

 Ø§ÙĦÙĦØºØ©

0.27

 Learning

0.27

Learning

0.27

Activations Density 0.271%

it

No Comments

No Known Activations