INDEX

Explanations

calculations/formulae/code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èīĩ

-0.29

.kafka

-0.27

mare

-0.26

áº¡ch

-0.26

#{

-0.26

attles

-0.25

tÃ³

-0.25

_feedback

-0.24

åįģå¹´

-0.24

 carrying

-0.24

POSITIVE LOGITS

HEMA

0.31

ailable

0.30

æıĸ

0.26

inel

0.25

 delta

0.24

æ¶Īæģ¯ç§°

0.24

oland

0.24

zano

0.24

iesta

0.24

"value

0.23

Activations Density 21.133%

calculations/formulae/code

No Comments

No Known Activations