INDEX

Explanations

wild

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 Firm

-0.27

::.

-0.26

Gos

-0.24

unless

-0.24

åľ¨è¿Ļç§į

-0.23

subsection

-0.23

endregion

-0.23

éĤ£æł·

-0.23

å±ķå¼Ģ

-0.23

"</

-0.23

POSITIVE LOGITS

cards

0.30

è¯¡

0.29

ä¸įå®ļ

0.28

 cardiac

0.27

fires

0.26

erals

0.25

ä¸įåħ¬å¹³

0.25

åŃĺåľ¨çĿĢ

0.25

åĺĪ

0.24

 rides

0.24

Activations Density 0.098%

wild

No Comments

No Known Activations