INDEX

Explanations

prefect

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çıŃ

-0.29

 cones

-0.25

ander

-0.25

å·²

-0.24

Ãłn

-0.24

ristol

-0.24

æĢĿèĢĥ

-0.23

æĥ³æĥ³

-0.23

istine

-0.23

 essays

-0.23

POSITIVE LOGITS

mium

0.30

teil

0.25

èµĽåĲİ

0.25

pun

0.24

mando

0.24

 Benchmark

0.24

ãĥĪãĥ©

0.23

 Gundam

0.23

 Seeder

0.22

çĶ°

0.22

Activations Density 6.549%

prefect

No Comments

No Known Activations