INDEX

Explanations

being alone/independent

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

Negative Logits

åįķçĭ¬

-0.45

çĭ¬èĩª

-0.45

èĩªè¡Į

-0.41

 alone

-0.40

-alone

-0.39

çĭ¬ç«ĭ

-0.37

 individually

-0.36

çĭ¬

-0.35

 separately

-0.35

èĩª

-0.35

POSITIVE LOGITS

 COVER

0.26

eer

0.24

InputStream

0.24

iring

0.23

 rings

0.23

ä¾¥å¹¸

0.23

.LENGTH

0.23

 heals

0.23

 propor

0.23

uple

0.22

Activations Density 0.012%

being alone/independent

No Known Activations