INDEX

Explanations

Orthodox

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĸ¹ä½į

-0.28

DialogContent

-0.26

{}".

-0.26

 partition

-0.26

æĭĴ

-0.25

åľ¨ä»Ĭå¹´

-0.25

.ordinal

-0.25

 negativity

-0.24

 Locker

-0.24

çļĦä¸Ģæ¬¾

-0.24

POSITIVE LOGITS

unks

0.28

uctose

0.28

-ves

0.27

æĬļ

0.26

 templ

0.25

ä½ĵç³»

0.25

Subsystem

0.25

Ibn

0.24

 novice

0.24

ONSE

0.24

Activations Density 0.179%

Orthodox

No Comments

No Known Activations