INDEX

Explanations

find

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

Not in Any Lists

No Comments

Negative Logits

pearance

-0.28

↵

-0.27

-0.26

æĥħåĨµä¸ĭ

-0.26

 conver

-0.25

 migrating

-0.25

 notable

-0.25

æİ¨åĲĳ

-0.25

 residual

-0.25

-0.24

POSITIVE LOGITS

 Bass

0.30

è¿ĻéĩĮ

0.28

èİ·å¾ĹæĽ´å¤ļ

0.28

 pronto

0.26

éĢĻè£¡

0.25

andes

0.25

ftware

0.25

cock

0.25

ãĥĬãĥ³

0.24

 Sark

0.24

Activations Density 0.019%

find

No Comments

No Known Activations