INDEX

Explanations

Programming code and documentation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_12.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.12.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĪĩ

-0.32

çĶµåŃĲäº§åĵģ

-0.28

lices

-0.26

åĪĢ

-0.26

ertain

-0.25

æ¼ł

-0.24

.selectAll

-0.23

ä¸§å¤±

-0.23

DEV

-0.23

åĲįåįķ

-0.23

POSITIVE LOGITS

æ¨¹

0.26

 tree

0.26

oving

0.25

 Confeder

0.25

utra

0.25

cre

0.24

æłĳ

0.24

ç§»åĬ¨

0.24

 conform

0.24

Tree

0.24

Activations Density 0.000%

Programming code and documentation

No Comments

No Known Activations