INDEX

Explanations

scientific/technical writing

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

stuff

-0.27

 itself

-0.27

 Stuff

-0.26

 stuff

-0.25

 drops

-0.25

as

-0.25

ary

-0.25

å°¬

-0.24

urry

-0.24

Pan

-0.24

POSITIVE LOGITS

rets

0.26

å´¦

0.25

 legs

0.24

è§Ħå®ļ

0.24

_keyword

0.24

ä¸ªèĤ¡

0.24

åĴĮåıĳå±ķ

0.23

ECM

0.23

åĽ½éĺ²éĥ¨

0.23

enames

0.23

Activations Density 0.007%

scientific/technical writing

No Comments

No Known Activations