INDEX

Explanations

Ordinal numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

way

-0.29

way

-0.29

Way

-0.29

ent

-0.29

ur

-0.28

æĸ¹å¼ı

-0.28

Way

-0.28

ETA

-0.27

WAY

-0.27

_way

-0.26

POSITIVE LOGITS

 Sixth

0.37

 Seventh

0.36

ç¬¬ä¸ĥ

0.31

 Third

0.31

onde

0.29

 Eighth

0.29

 Ninth

0.28

ÑĪÐ¸Ð²

0.28

Third

0.28

 seventh

0.27

Activations Density 0.011%

Ordinal numbers

No Comments

No Known Activations