INDEX

Explanations

Math and code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 third

-1.11

ç¬¬ä¸ī

-1.00

ç¬¬ä¸īä¸ª

-0.99

third

-0.96

 Third

-0.94

Third

-0.94

ç¬¬ä¸īæ¬¡

-0.85

 ÑĤÑĢÐµÑĤÑĮ

-0.83

-third

-0.82

 THIRD

-0.80

POSITIVE LOGITS

ennen

0.28

ighting

0.26

_DL

0.25

bundles

0.25

agra

0.25

 Spar

0.25

obl

0.24

åħ¥æĪ·

0.24

 Roths

0.24

Ãłng

0.23

Activations Density 0.004%

Math and code

No Comments

No Known Activations