INDEX

Explanations

families and friends

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

æ²»çĲĨ

-0.28

boards

-0.28

 Boards

-0.27

çıŃä¸»ä»»

-0.26

ÑĪÐºÐ¸

-0.25

yc

-0.25

igin

-0.25

olon

-0.25

 boards

-0.24

(td

-0.24

POSITIVE LOGITS

èº«å¤Ħ

0.27

ç¬ĳå£°

0.25

è®¾å¤ĩ

0.24

 trá»¯

0.24

 Lime

0.23

æ¡£

0.23

æĻ´

0.23

 electrom

0.23

TeV

0.23

pare

0.23

Activations Density 0.003%

families and friends

No Known Activations