INDEX

Explanations

Grip

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

lei

-0.27

 Ð½Ð°Ð»Ð¾Ð³Ð¾Ð²

-0.26

inceton

-0.25

sdale

-0.24

edException

-0.24

 Supplier

-0.23

åĪ©æ¶¦çİĩ

-0.23

 PROCUREMENT

-0.23

TAX

-0.23

 Honor

-0.23

POSITIVE LOGITS

rika

0.30

 polar

0.28

 positively

0.28

dde

0.28

ä¸įå¥½

0.28

ä¸Ńæľī

0.27

de

0.27

Activations Density 2.902%

Grip

No Comments

No Known Activations