INDEX

Explanations

programming/technical documentation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Telegram

-0.29

Advance

-0.27

ousand

-0.27

_advance

-0.27

 Telegram

-0.27

lucent

-0.26

åĮĸåĲĪ

-0.25

å²ĸ

-0.25

im

-0.25

anship

-0.25

POSITIVE LOGITS

æ¿Ģæ´»

0.30

aldi

0.27

ä½ıå®ħ

0.26

æĭ¾

0.25

inic

0.25

 spatial

0.24

 adjacency

0.24

å®ħ

0.24

ppy

0.24

à¸ªà¸Ļ

0.24

Activations Density 0.017%

programming/technical documentation

No Comments

No Known Activations