INDEX

Explanations

packages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 Money

-0.27

åģĥ

-0.26

 Tops

-0.25

ç°ĩ

-0.25

æĻ®éģį

-0.24

 recursion

-0.24

æģ¸

-0.24

 redesign

-0.24

coni

-0.24

stem

-0.24

POSITIVE LOGITS

pkg

0.43

/pkg

0.43

 PackageManager

0.42

pkg

0.38

-package

0.37

 Package

0.36

 package

0.36

 packaging

0.35

Package

0.35

.PackageManager

0.34

Activations Density 0.142%

packages

No Comments

No Known Activations