INDEX

Explanations

you will

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

è¾Ł

-0.31

å®£åĳĬ

-0.29

 restoration

-0.28

æĸ¥

-0.28

 resta

-0.27

çĴ©

-0.27

 pipe

-0.26

.defaults

-0.26

çĤ¼

-0.25

è§£æķ£

-0.24

POSITIVE LOGITS

Ð¾Ñī

0.29

WV

0.26

Advance

0.25

ovo

0.25

edb

0.25

æĦŁåºĶ

0.25

 Advance

0.25

anning

0.24

lov

0.24

eds

0.23

Activations Density 0.007%

you will

No Comments

No Known Activations