INDEX

Explanations

personal emails

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

ÑħÐ°

-0.27

å°±è¦ģ

-0.26

 spokes

-0.26

æĪĳä»¬è¦ģ

-0.25

à¸²à¸°

-0.25

atoi

-0.25

éĩĳå±±

-0.25

èĢ»

-0.25

UES

-0.24

åīĬ

-0.24

POSITIVE LOGITS

 might

0.32

 perhaps

0.32

 hope

0.31

 Could

0.30

 wondering

0.30

æĪĸè®¸

0.30

 hoping

0.30

 maybe

0.29

çĲĨæĥ³

0.28

ä¼ļä¸įä¼ļ

0.28

Activations Density 0.038%

personal emails

No Comments

No Known Activations