INDEX

Explanations

positive sentiment reviews/code

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

 prefer

-0.31

 Ð¾ÑĤÐºÐ°Ð·

-0.27

Rum

-0.26

 thÃŃch

-0.26

æ²īè¿·

-0.26

Ã¤ndig

-0.25

æĪ¿

-0.25

 preference

-0.25

 adher

-0.25

åĸľæ¬¢

-0.24

POSITIVE LOGITS

éĢļ

0.28

.getLocal

0.26

 hoped

0.26

åİĭç¼©

0.26

éªĮ

0.26

 lifes

0.25

é©Ĺ

0.25

éĶĨ

0.25

å§¹

0.25

calling

0.25

Activations Density 0.037%

positive sentiment reviews/code

No Comments

No Known Activations