INDEX

Explanations

URLs and code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pees

-0.29

Wh

-0.26

 peach

-0.25

åŀĭåı·

-0.24

ç¦»å¼Ģ

-0.24

pe

-0.24

åŀĭ

-0.24

ä»ĸä»¬ä¼ļ

-0.23

åį¸

-0.23

å¢ŀå¼ºäºĨ

-0.23

POSITIVE LOGITS

ç²Ĺ

0.29

ephy

0.28

erge

0.27

æ¨ª

0.27

atement

0.26

æ©«

0.25

æĥ³å¿µ

0.25

 (!((

0.25

atrix

0.24

esl

0.24

Activations Density 0.017%

URLs and code

No Comments

No Known Activations