INDEX

Explanations

Punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¯ķçĤ¹

-0.28

-head

-0.26

scores

-0.25

çļĦåĲĮæĹ¶

-0.25

ä¸Ģåı£æ°Ķ

-0.25

æ¦ĸ

-0.25

pitch

-0.25

¾ç¤º

-0.24

Specifier

-0.24

é¹ĺ

-0.23

POSITIVE LOGITS

æľīå¾Īå¤ļ

0.28

()._

0.27

è¿ĺæľīå¾Īå¤ļ

0.26

 Learning

0.25

 learning

0.25

Aim

0.25

åŃ¦æł¡çļĦ

0.25

è¿İ

0.25

uong

0.24

 cose

0.24

Activations Density 0.006%

Punctuation

No Comments

No Known Activations