INDEX

Explanations

,

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ragon

-0.29

 Ð·Ð°Ð½Ð¸Ð¼Ð°

-0.28

éģĹçķĻ

-0.24

å¦Ĥæľīä¾µæĿĥ

-0.24

 bÄĻdÄħ

-0.24

èµ³

-0.24

äº§åĩº

-0.24

æīĳ

-0.23

@s

-0.23

urers

-0.23

POSITIVE LOGITS

åĬĽè¿ĺæĺ¯

0.30

åĽłä¸ºå®ĥ

0.28

zed

0.27

 especially

0.27

 hire

0.27

æĦŁ

0.26

 because

0.26

åĽłä¸º

0.26

Ñī

0.25

 espec

0.25

Activations Density 0.987%

,

No Comments

No Known Activations