INDEX

Explanations

code and software projects

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

 Hawaiian

-0.34

æļĳ

-0.33

è®º

-0.31

 Hawaii

-0.29

ä¹¾åĿ¤

-0.28

 jungle

-0.28

åŀĤ

-0.27

è¿Ĥ

-0.25

Âł

-0.24

 Jungle

-0.24

POSITIVE LOGITS

æ¬§çĽŁ

0.47

.eu

0.37

 europ

0.37

æ¬§æ´²

0.36

 European

0.35

EU

0.35

europ

0.35

 Europ

0.34

 european

0.33

 Europe

0.32

Activations Density 0.102%

code and software projects

No Comments

No Known Activations