INDEX

Explanations

Programming/Scientific/Foreign Language

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

 Active

-0.26

 Ø´ÙĬ

-0.25

cheon

-0.25

fib

-0.25

æ²

-0.25

est

-0.25

 drag

-0.24

é£Ļ

-0.24

azines

-0.24

ä¸ľäº¬

-0.24

POSITIVE LOGITS

wards

0.33

urent

0.30

çī©

0.28

wers

0.28

ilyn

0.27

FromClass

0.26

inion

0.25

ç¾İ

0.25

ymes

0.25

.NewRequest

0.25

Activations Density 0.213%

Programming/Scientific/Foreign Language

No Known Activations