INDEX

Explanations

punctuation and code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

apel

-0.32

astery

-0.30

setParameter

-0.28

éķ¿çŁŃ

-0.26

ettel

-0.26

æĮĩæĮ¥

-0.25

onus

-0.25

[len

-0.25

åĳ¨å¹´

-0.25

etu

-0.25

POSITIVE LOGITS

di

0.29

uge

0.29

ior

0.27

ä¸»é¢ĺæ´»åĬ¨

0.27

 Intern

0.26

min

0.26

å½¢å®¹

0.25

.AutoScaleMode

0.25

ç»Ī

0.25

Activations Density 0.006%

punctuation and code

No Comments

No Known Activations