INDEX

Explanations

Software/technical contexts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surg

-0.29

.addTo

-0.27

AtIndex

-0.27

 installer

-0.26

æľĽ

-0.25

routine

-0.25

åłĤ

-0.25

æ¡¥

-0.24

 Scho

-0.24

ymb

-0.24

POSITIVE LOGITS

è·Łä»ĸ

0.31

è·Łä½ł

0.28

è·Łå¥¹

0.28

Collector

0.27

omnia

0.25

Ð±ÑĥÑĢ

0.25

 qualify

0.25

 trembling

0.24

æĪĳä¸ªäºº

0.24

èĺĳ

0.24

Activations Density 0.007%

Software/technical contexts

No Comments

No Known Activations