INDEX

Explanations

bar

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

ç¼º

-0.28

å¯ħ

-0.27

tet

-0.27

 authToken

-0.26

ram

-0.25

å®īæİĴ

-0.25

Tet

-0.25

åĦĩ

-0.24

ant

-0.24

æ»¡

-0.23

POSITIVE LOGITS

redicate

0.28

å¤§å®¶åĪĨäº«

0.27

ielding

0.26

çļĦä¹łæĥ¯

0.26

inea

0.25

ream

0.25

 prefixes

0.25

éĿŀè¦ģ

0.25

 habitats

0.25

IELD

0.24

Activations Density 0.096%

bar

No Comments

No Known Activations