INDEX

Explanations

data

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ainers

-0.26

etc

-0.26

ewis

-0.25

 Blueprint

-0.25

ä¸ĢéĿ¢

-0.25

 mist

-0.25

 clubs

-0.25

sticks

-0.25

)arg

-0.24

 setter

-0.24

POSITIVE LOGITS

ware

0.30

mere

0.29

 Sachs

0.28

acellular

0.28

æī¾

0.26

Ware

0.26

ä¸įéĶĪ

0.25

 judging

0.25

 republican

0.24

ä¸Ĭæµ·è¯ģåĪ¸

0.24

Activations Density 0.687%

data

No Comments

No Known Activations