INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

èİ·å¾ĹæĦŁ

-0.29

/process

-0.28

rs

-0.28

 tends

-0.26

 alike

-0.26

 Ã¼zere

-0.25

WC

-0.25

 Â«

-0.24

metic

-0.24

Ð¾Ð±Ñĭ

-0.24

POSITIVE LOGITS

agara

0.27

çµ®

0.26

ONSE

0.26

 Kata

0.25

ANGO

0.25

DownList

0.25

sey

0.25

ä¸įå½±åĵį

0.25

.ci

0.25

.are

0.25

Activations Density 0.141%

Code

No Known Activations