INDEX

Explanations

particle physics

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

 Licensed

-0.29

Clar

-0.25

enet

-0.25

Ĥ¬

-0.25

 TextAlign

-0.24

 licensors

-0.24

ÐķÐĿ

-0.24

æģ©

-0.24

 HOWEVER

-0.24

 Clar

-0.24

POSITIVE LOGITS

.den

0.30

è¿ĺçľŁ

0.27

_hard

0.26

ä¸īä»£

0.26

DOC

0.26

 denomin

0.26

à¸¢à¸²à¸¢

0.25

 denom

0.25

Ã¶t

0.25

_EVT

0.24

Activations Density 11.905%

particle physics

No Comments

No Known Activations