INDEX

Explanations

especially

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

ãĥ¼ãĥ³

-0.29

èµī

-0.29

tain

-0.28

 lanc

-0.27

ikt

-0.27

ramid

-0.25

 METHOD

-0.25

urance

-0.24

etur

-0.24

-method

-0.24

POSITIVE LOGITS

uper

0.29

<!--

0.27

unday

0.27

ARIO

0.26

 Regression

0.26

æĹłæīĢ

0.26

ponents

0.25

äºĨåĩºæĿ¥

0.24

 Grand

0.24

ç²¾ç¥ŀæĸĩæĺİ

0.24

Activations Density 0.017%

especially

No Comments

No Known Activations