INDEX

Explanations

numbers and counting

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Submission

-0.29

rias

-0.27

mits

-0.27

erp

-0.26

rier

-0.26

submission

-0.26

 submission

-0.25

Submission

-0.25

å¤¸å¼ł

-0.24

ollo

-0.24

POSITIVE LOGITS

 itself

0.28

æĪĳä»¬ä¹Ł

0.26

 prem

0.26

å¾ª

0.26

 arena

0.25

@g

0.25

è¿Ļä¸ªæĹ¶åĢĻ

0.24

.inc

0.24

 correlations

0.24

silent

0.23

Activations Density 4.293%

numbers and counting

No Comments

No Known Activations