INDEX

Explanations

software licenses and open source

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

osl

-0.28

-paying

-0.27

åħįè´¹

-0.26

åį¡

-0.26

µ

-0.26

andon

-0.26

ÐµÐº

-0.25

andan

-0.25

 Ð¾ÑĢÐ³Ð°Ð½Ð¸Ð·Ð°ÑĨÐ¸Ñı

-0.24

bish

-0.24

POSITIVE LOGITS

æ»¡æ»¡çļĦ

0.30

åı£æ°Ķ

0.29

peated

0.27

åķĨæĬ¥

0.27

holm

0.27

 Mansion

0.27

 pund

0.26

çªģåĩºéĹ®é¢ĺ

0.25

åĩºåĬ¨

0.24

ä¸¤çĤ¹

0.24

Activations Density 0.024%

software licenses and open source

No Comments

No Known Activations