INDEX

Explanations

Technical/Scientific documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inas

-0.28

imax

-0.27

 Emer

-0.25

inf

-0.24

æį»

-0.24

eman

-0.24

ç¼ļ

-0.24

enas

-0.24

ystems

-0.24

 Matters

-0.23

POSITIVE LOGITS

ä»ĩ

0.27

atorio

0.27

éĿ¢

0.27

åĺ¹

0.27

å®ŀä½ĵ

0.27

å¤§æĪĺ

0.26

 Costa

0.26

 design

0.26

è®¾è®¡

0.25

åĪ¶

0.25

Activations Density 0.001%

Technical/Scientific documents

No Comments

No Known Activations