INDEX

Explanations

science or technical text

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

åºŃ

-0.30

deck

-0.27

rum

-0.27

çĽĴ

-0.27

atform

-0.26

è¢ĭ

-0.26

ElementType

-0.25

éĽ¶

-0.25

ighest

-0.24

ä¸ĭæĿ¥

-0.24

POSITIVE LOGITS

MEDIA

0.30

anness

0.27

ĽĦ

0.27

ç¨·

0.27

èģĶç³»

0.26

æĺİçŁ¥

0.26

 ageing

0.26

ampp

0.25

 ought

0.25

å§ĳ

0.24

Activations Density 0.035%

science or technical text

No Comments

No Known Activations