INDEX

Explanations

dynasty

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

æ·¡åĮĸ

-0.29

tures

-0.29

åİĮ

-0.27

åı¦ä¸Ģä½į

-0.26

anken

-0.26

kes

-0.26

é¡¾

-0.25

SMP

-0.25

éĿ©

-0.25

ä»²

-0.25

POSITIVE LOGITS

èŃ·

0.29

èľĪ

0.28

èŃ¬å¦Ĥ

0.27

egree

0.26

egie

0.26

aptcha

0.26

washer

0.25

 stake

0.24

çĽĺçĤ¹

0.24

 tempList

0.24

Activations Density 0.003%

dynasty

No Comments

No Known Activations