INDEX

Explanations

period

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

quo

-0.29

extField

-0.28

emb

-0.27

 whatsoever

-0.26

å¼łæī¬

-0.26

 mentally

-0.25

èĪĮ

-0.25

_lane

-0.24

 mental

-0.24

 unborn

-0.24

POSITIVE LOGITS

ãģĦãģŁãģłãģĦãģ¦

0.28

<![

0.26

ä»ĸæĺ¯

0.25

æĹ¨åľ¨

0.25

çĽ®çļĦæĺ¯

0.24

ippi

0.24

æĸ¹å¼ıè¿Ľè¡Į

0.24

Ð¸ÑĢÑĥÐµÑĤÑģÑı

0.24

ä¸ĵæ³¨äºİ

0.24

_requirements

0.24

Activations Density 0.936%

period

No Comments

No Known Activations