INDEX

Explanations

World

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

those

-0.29

ritz

-0.28

æĢ»éĺŁ

-0.28

åĮºå§Ķ

-0.27

 those

-0.26

 retal

-0.26

StateManager

-0.25

rides

-0.25

ç§ĳæĬĢèĤ¡ä»½

-0.24

"<?

-0.24

POSITIVE LOGITS

æ¯ĶèµĽ

0.33

çº§åĪ«çļĦ

0.29

çº§åĪ«

0.29

æ¯ĶèµĽä¸Ń

0.27

procedure

0.27

 procedure

0.27

åĬŀå¥½

0.26

Ð°ÑĨÐ¸Ð¾Ð½

0.26

stop

0.26

æĵįä½ľ

0.25

Activations Density 0.014%

World

No Comments

No Known Activations