INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_4.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.4.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 subjects

-0.27

 Subjects

-0.27

.subject

-0.26

æ¬¢

-0.25

 subject

-0.25

 clinics

-0.25

åĲĦæł·

-0.25

Subjects

-0.25

iciones

-0.24

å®¤å¤ĸ

-0.24

POSITIVE LOGITS

premium

0.28

agus

0.26

(nc

0.26

 premiums

0.25

 premium

0.25

é¦ĸå¯Į

0.25

rone

0.25

OTE

0.25

nc

0.25

Ð¿ÑĥÑĤ

0.24

Activations Density 1.597%

code

No Comments

No Known Activations