INDEX

Explanations

ware

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

 Bris

-0.31

assy

-0.26

_BINDING

-0.25

ortho

-0.25

cheid

-0.25

 MessageType

-0.25

orns

-0.24

 getMessage

-0.24

rbrace

-0.24

odi

-0.24

POSITIVE LOGITS

0.38

0.32

0.29

mh

0.29

 embedded

0.27

è¯Ŀ

0.27

ps

0.27

åĲ¸

0.27

 punched

0.25

eus

0.25

Activations Density 0.036%

ware

No Comments

No Known Activations