INDEX

Explanations

and

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

 digest

-0.30

éĤ£ä»½

-0.29

ä¸Ģåıªæīĭ

-0.26

-Version

-0.26

unb

-0.25

und

-0.25

æ¶ĪåĮĸ

-0.24

 last

-0.24

ä¸Ģä»½

-0.24

last

-0.24

POSITIVE LOGITS

èµłéĢģ

0.29

ello

0.26

æĸ°éĹ»ä¸Ńå¿ĥ

0.26

æĪĳä»¬ä¼ļ

0.25

åı¯ä»¥èİ·å¾Ĺ

0.25

orean

0.25

éĺ¿æ£®

0.24

 tweeting

0.24

(:,:,

0.24

å°±ä¸įä¼ļ

0.23

Activations Density 0.008%

and

No Comments

No Known Activations