INDEX

Explanations

numbers and code

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

 Costa

-0.25

ButtonType

-0.24

æĢ»çĲĨ

-0.24

Ð»Ð°Ð³Ð°

-0.24

åı²

-0.24

 Commons

-0.24

ç´ł

-0.24

agan

-0.24

affe

-0.23

Ð»Ð¸Ñĩ

-0.23

POSITIVE LOGITS

sync

0.28

å·¥å§Ķ

0.27

 maxim

0.26

è¾Ĳ

0.26

OfWork

0.26

lobal

0.25

ÊĮ

0.25

Max

0.24

 untranslated

0.24

æĻŀ

0.24

Activations Density 0.079%

numbers and code

No Comments

No Known Activations