INDEX

Explanations

apt

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĦ¶æĺ¯

-0.25

 exchanged

-0.25

hoot

-0.25

åºĨå¹¸

-0.25

 Prefer

-0.25

ç©ºåīį

-0.24

ç¼ºå¸Ń

-0.24

OUSE

-0.24

 sinon

-0.23

ÑīÑĥ

-0.23

POSITIVE LOGITS

itude

0.43

ulet

0.32

ness

0.31

ibility

0.31

orn

0.31

ury

0.29

oring

0.29

itudes

0.28

æĮģãģ¡

0.28

inity

0.27

Activations Density 0.362%

apt

No Comments

No Known Activations