INDEX

Explanations

the

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

ConfigurationException

-0.26

enger

-0.25

AE

-0.24

 notes

-0.24

CHAR

-0.24

AE

-0.24

ç¡Ģ

-0.23

 Makeup

-0.23

 ÑĤÐ¾Ð¼

-0.23

UPDATED

-0.23

POSITIVE LOGITS

è·ĳåĪ°

0.27

bars

0.27

ä¹łæĥ¯

0.26

åħļåĴĮ

0.26

onal

0.26

lessly

0.26

coma

0.26

 migrate

0.25

hsi

0.24

çŀ½

0.24

Activations Density 15.424%

the

No Comments

No Known Activations