INDEX

Explanations

punctuation marks

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

áº¿n

-0.26

 maybe

-0.26

eworld

-0.25

ãģłãģĮ

-0.25

å¤§å®¶

-0.25

onne

-0.25

(graph

-0.24

äººå®¶

-0.24

Ð¾Ð»ÑĥÑĩ

-0.23

åħ¶å®ŀæĺ¯

-0.23

POSITIVE LOGITS

 note

0.42

 Note

0.35

Note

0.31

ä¸įæĪĲ

0.29

note

0.29

 moreover

0.29

åĲĮæĹ¶è¿ĺ

0.28

è¯·æ³¨æĦı

0.28

æŃ¤å¤ĸ

0.28

_note

0.28

Activations Density 0.002%

punctuation marks

No Comments

No Known Activations