INDEX

Explanations

punctuation

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

anders

-0.30

áº©

-0.27

æĪĳè§īå¾Ĺ

-0.26

Tab

-0.25

 Shell

-0.25

 Bend

-0.24

æĪĳæĥ³

-0.24

åĪ°åºķæĺ¯

-0.24

à¹Ģà¸ļ

-0.24

ci

-0.23

POSITIVE LOGITS

olley

0.27

èĥ¥

0.27

omm

0.26

æĶ»åĬ¿

0.26

ammu

0.25

"'.

0.24

ows

0.24

">'.

0.23

 Directors

0.23

 JFactory

0.23

Activations Density 0.012%

punctuation

No Known Activations