INDEX

Explanations

equals sign

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

strap

-0.28

ListNode

-0.27

oreach

-0.26

sembl

-0.25

 condemned

-0.25

rut

-0.25

rolling

-0.24

 coupling

-0.24

ERO

-0.24

lying

-0.24

POSITIVE LOGITS

ç³ķ

0.27

workspace

0.26

Ø§Ø±ÙĬØ©

0.25

éļ¨

0.25

.Series

0.25

chip

0.25

æľīæĹ¶

0.24

 Ð¿Ð¾Ð¿

0.24

.getLog

0.24

spa

0.23

Activations Density 0.013%

equals sign

No Comments

No Known Activations