INDEX

Explanations

root

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

MZ

-0.29

çļĦæľįåĬ¡

-0.27

Ã¡b

-0.27

avra

-0.26

çģ«

-0.25

bÃ©

-0.25

oster

-0.24

çĦ°

-0.24

 trÃº

-0.24

ç£ĭåķĨ

-0.24

POSITIVE LOGITS

own

0.25

.hasMore

0.25

major

0.24

(det

0.24

det

0.24

elly

0.24

éĽĨæĪĲ

0.23

æĮŀ

0.23

æ¹Ľ

0.23

 arte

0.23

Activations Density 0.044%

root

No Comments

No Known Activations