INDEX

Explanations

ocean

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

rect

-0.28

uttle

-0.27

indle

-0.27

useum

-0.25

å±ķè§Ī

-0.25

 passage

-0.25

aland

-0.25

rice

-0.25

å¹¶åĲĳ

-0.24

 rect

-0.24

POSITIVE LOGITS

 undercut

0.31

LICENSE

0.27

 razor

0.27

å¤ĸåĽ½äºº

0.27

bos

0.26

iesen

0.24

é¥®

0.24

éļıå¤Ħåı¯è§ģ

0.24

(coder

0.24

_filters

0.23

Activations Density 0.014%

ocean

No Comments

No Known Activations