INDEX

Explanations

seconds

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

å®ŀ

-0.30

-0.28

-REAL

-0.28

cast

-0.28

untlet

-0.26

è·¯çĶ±

-0.26

ä¸įè¶³

-0.25

æĪĳåĽ½

-0.25

castle

-0.25

cores

-0.25

POSITIVE LOGITS

éĤ£äºº

0.28

enser

0.27

 Caval

0.27

 Maher

0.27

ç¼Ĺ

0.25

 NavController

0.25

çĺģ

0.24

 closet

0.23

éĴ¿

0.23

apons

0.23

Activations Density 31.902%

seconds

No Comments

No Known Activations