INDEX

Explanations

various topics

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

clar

-0.28

ä¹°çļĦ

-0.27

æĺ¯æĪĳçļĦ

-0.27

 customizable

-0.27

bben

-0.26

åŃ¥

-0.25

èĭ¥æĤ¨

-0.25

ãģ£ãģ½

-0.24

_customize

-0.24

Ð¿ÑĢÐ¾ÑĦÐµÑģÑģÐ¸Ð¾Ð½Ð°Ð»

-0.24

POSITIVE LOGITS

æĺ¯åĲ¦

0.86

 whether

0.82

èĥ½åĲ¦

0.78

whether

0.77

 Whether

0.71

æĺ¯åĲ¦ä¼ļ

0.71

 æĺ¯åĲ¦

0.71

ä¸İåĲ¦

0.69

èĥ½ä¸įèĥ½

0.66

ä½ķæĹ¶

0.64

Activations Density 0.002%

various topics

No Comments

No Known Activations