INDEX

Explanations

lightweight

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

ermen

-0.28

.NULL

-0.27

çļĦåİĭåĬĽ

-0.26

lon

-0.26

ude

-0.26

esis

-0.26

 hides

-0.25

 spons

-0.25

.CopyTo

-0.24

ernity

-0.24

POSITIVE LOGITS

æĦıæĢĿ

0.27

 monoc

0.26

åŃ¦èĢħ

0.25

ÑĮÑı

0.25

æŃ»èĢħ

0.24

 Hurt

0.23

 Schul

0.23

belt

0.23

ç²¹

0.23

 Mand

0.23

Activations Density 0.159%

lightweight

No Comments

No Known Activations