INDEX

Explanations

Code/URLs/Columbus

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ´Ĺ

-0.32

 wash

-0.31

:checked

-0.26

è¡¨çİ°ä¸º

-0.25

 washed

-0.24

æīĺ

-0.24

-chevron

-0.24

åĪĹä¸º

-0.23

åĪĴ

-0.23

æīĭä¸ĭ

-0.23

POSITIVE LOGITS

gene

0.30

OLD

0.28

é¸¢

0.28

éŀĭ

0.28

 stresses

0.27

çĶ³è´Ń

0.25

ä¸įéĹ´

0.25

 Union

0.24

 localVar

0.24

icorn

0.24

Activations Density 0.020%

Code/URLs/Columbus

No Comments

No Known Activations