INDEX

Explanations

zero

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

abee

-0.28

 Explanation

-0.28

ped

-0.26

idar

-0.26

arn

-0.26

tri

-0.26

_tri

-0.26

 metre

-0.25

Explanation

-0.25

cel

-0.25

POSITIVE LOGITS

 Ð´Ð²Ð¸Ð³

0.29

è§ī

0.28

è¦º

0.26

åľ°ä¸ĭ

0.26

 emerging

0.25

áºŃu

0.24

å¼Ģå±Ģ

0.24

 tail

0.24

oke

0.24

 deemed

0.23

Activations Density 0.104%

zero

No Comments

No Known Activations