INDEX

Explanations

code/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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 anymore

-0.36

ä¹Łä¸įåı¯èĥ½

-0.34

yet

-0.33

yet

-0.32

æľīä»»ä½ķ

-0.31

nor

-0.30

Yet

-0.29

Yet

-0.29

äº§çĶŁäºĨ

-0.28

 necessarily

-0.26

POSITIVE LOGITS

 most

0.26

%+

0.25

 ordinance

0.25

æĿĢäºĨ

0.24

è¿ĺæĺ¯è¦ģ

0.24

æ¯Ķè¾ĥå¤ļ

0.24

 mostly

0.23

ä¹Ī

0.23

doc

0.23

Most

0.23

Activations Density 0.004%

code/technical writing

No Comments

No Known Activations