INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lek

-0.29

ayout

-0.28

ibrary

-0.26

 basics

-0.26

ights

-0.25

æĻ®

-0.25

lei

-0.25

lyph

-0.24

ight

-0.24

achs

-0.24

POSITIVE LOGITS

#error

0.28

è¿ĺæľīä»Ģä¹Ī

0.27

mc

0.26

ä¸įçŁ¥éģĵ

0.26

ä¸ĢéĿ¢

0.23

è°ģçŁ¥

0.23

reasonable

0.23

ort

0.23

 Strikes

0.23

é²Ń

0.23

Activations Density 0.050%

punctuation

No Comments

No Known Activations