INDEX

Explanations

Scientific/Technical topics

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

<fieldset

-0.31

åįĩéĻį

-0.30

compass

-0.29

 controls

-0.26

æİ§

-0.26

ä¼¸

-0.25

 detects

-0.25

uj

-0.25

velle

-0.24

charm

-0.24

POSITIVE LOGITS

æľº

0.29

 Rent

0.27

å¯Ħ

0.26

çļĦçľ¼

0.25

reta

0.25

 tutoring

0.24

ForResource

0.24

rush

0.24

 hosted

0.24

 rented

0.24

Activations Density 0.007%

Scientific/Technical topics

No Comments

No Known Activations