INDEX

Explanations

to

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

('*',

-0.27

æ·±å±Ĥ

-0.26

 inputs

-0.26

ä¸ªé¡¹çĽ®

-0.26

_inputs

-0.25

_ORIGIN

-0.25

 Inputs

-0.25

mess

-0.24

ãģ£ãģįãĤĬ

-0.24

(EXPR

-0.24

POSITIVE LOGITS

åıĳå¸ĥçļĦ

0.29

 domest

0.29

 domestic

0.27

 demi

0.27

 Domestic

0.27

éĤĳ

0.26

ViewById

0.26

.ev

0.24

çĶŁäº§çļĦ

0.24

 Native

0.24

Activations Density 0.040%

to

No Comments

No Known Activations