INDEX

Explanations

Regions and Locations

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

 Belgi

-0.27

obia

-0.26

ortion

-0.25

ours

-0.24

Anywhere

-0.24

 youths

-0.24

olini

-0.24

ATAR

-0.24

itions

-0.23

æ°ĳä¸»åħļ

-0.23

POSITIVE LOGITS

0.29

 champ

0.28

 Little

0.28

è¿ĻæĿ¡

0.28

</

0.27

 Long

0.27

Un

0.26

Activations Density 0.013%

Regions and Locations

No Comments

No Known Activations