INDEX

Explanations

Wall

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ive

-0.29

 lÃ¥

-0.26

ltk

-0.25

.uuid

-0.24

IFY

-0.24

RON

-0.24

 Perc

-0.24

Ð¸Ð¾Ð½Ð°

-0.23

ML

-0.23

ount

-0.23

POSITIVE LOGITS

abouts

0.27

åīįåĪĹ

0.26

ArgsConstructor

0.25

çļĦèº«ä½ĵ

0.25

å¯¹æİ¥

0.25

åĪ¶åĵģ

0.25

 derived

0.25

Yay

0.24

çŃīæĸ¹éĿ¢

0.24

æ§ĺ

0.24

Activations Density 38.262%

Wall

No Comments

No Known Activations