INDEX

Explanations

Code and Technical Writing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¹Ľ

-0.31

eper

-0.29

anza

-0.28

AZE

-0.28

 spared

-0.28

 spare

-0.26

adal

-0.26

 sparing

-0.25

 prÃ¡ctica

-0.24

mx

-0.24

POSITIVE LOGITS

çĿĢ

0.27

 Charter

0.27

 Tell

0.27

IFI

0.25

æĿ¡ä»¶

0.24

è½®

0.24

å®ļ

0.24

ersion

0.24

Rat

0.23

 charter

0.23

Activations Density 0.001%

Code and Technical Writing

No Comments

No Known Activations