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

Not in Any Lists

No Comments

Negative Logits

.volley

-0.27

ä¹Łåıªæľī

-0.25

Ã¼l

-0.25

chts

-0.25

 argument

-0.24

enty

-0.24

ä¸ĭéĿ¢

-0.24

ul

-0.23

ightly

-0.23

 showAlert

-0.23

POSITIVE LOGITS

èĩĬ

0.26

æĮĩå°ĸ

0.26

ä¹łæĥ¯

0.26

ope

0.26

ìŀ¬

0.25

{@

0.24

é¡·

0.24

 Beats

0.23

 Canonical

0.23

vog

0.23

Activations Density 0.002%

punctuation

No Comments

No Known Activations