INDEX

Explanations

qualifications, candidates

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Natur

-0.27

ä¸įæĺ¯ä¸Ģä¸ª

-0.26

è¿Ļæĺ¯ä¸Ģä¸ª

-0.25

ians

-0.24

è¯Ŀè¯´

-0.24

main

-0.24

_qp

-0.23

 Shia

-0.23

åºŁ

-0.23

 totalTime

-0.23

POSITIVE LOGITS

 factor

0.28

vention

0.27

æļĹ

0.26

emploi

0.25

ogg

0.25

 Factor

0.24

è¯±åıĳ

0.24

æµ·æ£ł

0.24

tls

0.24

 prov

0.24

Activations Density 0.002%

qualifications, candidates

No Comments

No Known Activations