INDEX

Explanations

the

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

æŀķ

-0.30

WER

-0.28

nung

-0.27

.dtp

-0.25

mith

-0.25

ipop

-0.25

 Webb

-0.25

è¯¥éĻ¢

-0.25

 Howe

-0.24

went

-0.24

POSITIVE LOGITS

åŃĺéĩı

0.33

zero

0.25

å¯¹ä»ĸä»¬

0.24

Towards

0.24

closing

0.24

Closing

0.24

 specified

0.23

æĮĩå®ļ

0.23

bv

0.23

.utf

0.23

Activations Density 0.044%

the

No Comments

No Known Activations