INDEX

Explanations

code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

utting

-0.28

FY

-0.27

Advertisement

-0.26

ä¸įèĥ½ä¸ºç©º

-0.25

 Caldwell

-0.25

iable

-0.25

ctest

-0.25

urpose

-0.25

 Fountain

-0.24

æľªæĪĲ

-0.24

POSITIVE LOGITS

ucas

0.27

(fn

0.26

ÐµÑģÑĤÐ²Ð¾

0.25

 Disco

0.25

 Stereo

0.25

mite

0.25

 reuseIdentifier

0.24

å¤ĩ

0.24

çķĻ

0.24

Ø§ØªÙĩØ§

0.23

Activations Density 0.278%

code

No Comments

No Known Activations