INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arna

-0.29

urring

-0.29

phia

-0.25

-Encoding

-0.25

ä¸įåĪĨ

-0.25

CY

-0.25

-fe

-0.25

çļĦåģļæ³ķ

-0.24

-ar

-0.24

angelo

-0.24

POSITIVE LOGITS

lÃ¢

0.26

idades

0.25

itles

0.25

icts

0.25

 Spit

0.24

ÑĩÐ¸Ðº

0.24

æİĴ

0.23

æ¢¯éĺŁ

0.23

/tasks

0.23

ouble

0.23

Activations Density 1.039%

Code

No Comments

No Known Activations