INDEX

Explanations

companies

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æķĪ

-0.31

åĲĳä¸ĭ

-0.28

ikon

-0.26

æ³ķå¾ĭè§Ħå®ļ

-0.25

nom

-0.25

æ³ķä»¤

-0.25

CG

-0.25

ä¼łè¾ĵ

-0.24

rine

-0.24

 Conn

-0.24

POSITIVE LOGITS

uddy

0.28

ArrayType

0.24

qualities

0.24

ustrial

0.24

alties

0.24

 theater

0.23

æĸĩèīº

0.23

æ´ģ

0.23

ç§«

0.23

unted

0.23

Activations Density 50.593%

companies

No Comments

No Known Activations