INDEX

Explanations

punctuation marks

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĤº

-0.29

 Dexter

-0.27

éģĩ

-0.26

kah

-0.24

Additionally

-0.24

Ã¦r

-0.24

/avatar

-0.24

uchos

-0.24

/lib

-0.24

dep

-0.24

POSITIVE LOGITS

 recent

0.37

æľĢè¿ĳ

0.31

 previous

0.31

éĢĻä¸Ģ

0.30

recent

0.30

ä¹ĭåīįçļĦ

0.30

çĽ®åīįå·²

0.29

è¿Ļæĺ¯æĪĳä»¬

0.29

çĽ®åīįå·²ç»ı

0.29

æľ¬è½®

0.28

Activations Density 0.904%

punctuation marks

No Comments

No Known Activations