INDEX

Explanations

technical writing

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

landscape

-0.27

.DialogInterface

-0.27

 Ð²ÑĭÐ³Ð¾Ð´

-0.27

edy

-0.26

è®¢è´Ń

-0.26

decay

-0.26

 deposited

-0.25

decrypt

-0.25

 rotten

-0.25

 Continental

-0.25

POSITIVE LOGITS

èº«ä½ĵ

0.41

çļĦèº«ä½ĵ

0.35

éª¨éª¼

0.33

 Ð·Ð´Ð¾ÑĢÐ¾Ð²

0.33

èº«é«Ķ

0.33

èº«ä½ĵåģ¥åº·

0.32

,body

0.29

åĮ»åŃ¦

0.29

æģ¯

0.29

Ã§o

0.29

Activations Density 9.835%

technical writing

No Comments

No Known Activations