INDEX

Explanations

1

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sand

-0.51

æ²Ļ

-0.47

 Sand

-0.46

æ³¥

-0.44

å°ĺ

-0.43

 sands

-0.42

 dust

-0.41

çłĤ

-0.40

å¡µ

-0.39

æ²Ļæ»©

-0.39

POSITIVE LOGITS

.REACT

0.26

rale

0.25

é¦Ļæ°´

0.24

 Kindle

0.24

èıĩ

0.24

å½ĸ

0.24

 Levi

0.24

mailer

0.23

jQuery

0.23

 optical

0.23

Activations Density 0.103%

1

No Comments

No Known Activations