INDEX

Explanations

comparison

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è§Ħ

-0.30

])**

-0.28

iram

-0.28

dre

-0.27

åĤ¬

-0.25

’B

-0.25

dac

-0.25

éĢĥ

-0.25

 tagging

-0.24

ottom

-0.24

POSITIVE LOGITS

çķĢ

0.26

çľģå¸Ĥ

0.26

åľī

0.25

ä¸ĢæĹı

0.25

sta

0.25

 Ð¿Ð¾Ð¼

0.24

unitÃł

0.24

CHAT

0.24

ADDRESS

0.23

ä¸Ģç«Ļ

0.23

Activations Density 15.565%

comparison

No Comments

No Known Activations