INDEX

Explanations

local areas and communities

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 sourceMappingURL

-0.28

 numRows

-0.27

domains

-0.26

ieri

-0.26

 regimes

-0.26

.ErrorCode

-0.25

_domains

-0.24

ufacturer

-0.24

è¾ĸåĮºåĨħ

-0.24

 domains

-0.24

POSITIVE LOGITS

 area

0.38

 general

0.37

Area

0.35

(area

0.33

ä¸ĢèĪ¬

0.32

general

0.31

	area

0.31

area

0.30

 Area

0.30

ä¸ĢèĪ¬çļĦ

0.29

Activations Density 0.144%

local areas and communities

No Known Activations