INDEX

Explanations

glass (noun)

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

bare

-0.28

ellar

-0.28

flo

-0.27

å®¹è²Į

-0.27

ard

-0.26

ä¸įä»£è¡¨

-0.26

ollen

-0.26

 prim

-0.26

Tos

-0.25

ÑģÐ¾Ð²

-0.25

POSITIVE LOGITS

afia

0.30

å¤«äºº

0.27

pcl

0.27

eneric

0.26

å°ıåŃĲ

0.25

¾

0.25

è¿ĺæĥ³

0.24

å¤§åıĶ

0.24

 Arrays

0.24

holders

0.24

Activations Density 0.001%

glass (noun)

No Comments

No Known Activations