INDEX

Explanations

plate

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/ap

-0.28

grand

-0.27

éĨļ

-0.27

æĤ¬å¿µ

-0.26

Grand

-0.25

/per

-0.24

esc

-0.24

Brief

-0.23

dent

-0.23

 escaping

-0.23

POSITIVE LOGITS

 plates

0.31

imiter

0.28

_plate

0.27

plates

0.26

 plate

0.26

ayment

0.25

oldown

0.25

 Rosenstein

0.25

éłĺ

0.24

 Plates

0.24

Activations Density 15.068%

plate

No Comments

No Known Activations