INDEX

Explanations

biological energy/phosphorylation

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

æĮĩçĶ²

-0.30

ixon

-0.26

ä¸ĭéĽ¨

-0.26

ialis

-0.26

 errorMessage

-0.24

 cult

-0.24

ìľĪ

-0.24

mam

-0.24

Pat

-0.24

éĿŀ

-0.24

POSITIVE LOGITS

 Charges

0.29

ifetime

0.28

è¹Ī

0.28

å¢ŀåĬłåĢ¼

0.27

åĩłæŃ¥

0.26

 Roose

0.26

è¿Ļæī¹

0.26

 charges

0.26

notations

0.25

æĮ£éĴ±

0.24

Activations Density 1.612%

biological energy/phosphorylation

No Comments

No Known Activations