INDEX

Explanations

ios

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

inion

-0.29

 fair

-0.28

Ã©nom

-0.27

 auprÃ¨s

-0.27

fair

-0.26

 capture

-0.26

age

-0.26

 stations

-0.26

 captures

-0.25

å²ģ

-0.25

POSITIVE LOGITS

åŁł

0.25

æİ¥åĲ¬

0.25

 thereafter

0.25

 purse

0.25

è½¬æĬĺ

0.25

 textStyle

0.25

rops

0.24

 endPoint

0.24

ould

0.24

ä¸ĢåĪĩéĥ½æĺ¯

0.23

Activations Density 0.001%

ios

No Comments

No Known Activations