INDEX

Explanations

studies involving numbers and sizes

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

aler

-0.26

mage

-0.26

anus

-0.26

mist

-0.25

å¾ķ

-0.25

washer

-0.24

 Affero

-0.24

 fringe

-0.24

å®ŀè´¨æĢ§

-0.24

ä¸ŃåĽ½ä¼łç»Ł

-0.23

POSITIVE LOGITS

cha

0.27

erts

0.26

ethyl

0.26

æĿĢ

0.26

curity

0.26

 TÆ°

0.25

 Ivory

0.24

è¨Ģ

0.24

 goals

0.23

Activations Density 0.006%

studies involving numbers and sizes

No Comments

No Known Activations