INDEX

Explanations

9

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stands

-0.32

ç«Ļåľ¨

-0.31

_stand

-0.29

 stand

-0.28

åıĤ

-0.27

 standpoint

-0.27

è£ķ

-0.26

cup

-0.26

åĬ¿

-0.26

stand

-0.26

POSITIVE LOGITS

odor

0.27

æĨĻ

0.26

epy

0.25

 beauty

0.25

orary

0.24

resh

0.24

 ember

0.24

getOption

0.24

 OPTIONS

0.24

tor

0.24

Activations Density 0.004%

9

No Comments

No Known Activations