INDEX

Explanations

adopt

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

å¤ĸåĮħ

-0.30

æ¸¸

-0.28

contract

-0.27

éĩįå·¥

-0.25

contain

-0.24

hydr

-0.24

voz

-0.24

izes

-0.23

leased

-0.23

 gode

-0.23

POSITIVE LOGITS

 nations

0.26

ÐµÐ»Ð°

0.25

alom

0.25

ENTRY

0.24

TEE

0.23

{:

0.23

.twig

0.23

åĲĮè¡Į

0.23

 toArray

0.23

æĪĲåĳĺåĽ½

0.23

Activations Density 0.213%

adopt

No Known Activations