INDEX

Explanations

one

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_CONFIGURATION

-0.28

 Weekly

-0.26

 uncomment

-0.25

 configuration

-0.24

ç½ĺ

-0.24

æ©ĩ

-0.24

ero

-0.24

hift

-0.23

Configuration

-0.23

Weekly

-0.23

POSITIVE LOGITS

èĽĭ

0.25

çĿĢçľ¼

0.25

åĲ«

0.24

è®¸

0.23

éĩĩæĳĺ

0.23

æĶ¶ç¼©

0.23

Ð¾ÑĦ

0.23

åŃ¦ä½į

0.23

nor

0.23

inte

0.23

Activations Density 0.206%

one

No Comments

No Known Activations