INDEX

Explanations

Nostalgia/memories

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enc

-0.33

-aff

-0.29

éģĩ

-0.28

å¯¹å¾ħ

-0.28

aff

-0.28

è®©åŃ¦çĶŁ

-0.27

è®©ä»ĸä»¬

-0.27

aff

-0.26

inf

-0.26

entialAction

-0.26

POSITIVE LOGITS

st

0.30

å¼łè´´

0.27

ialog

0.27

 Floor

0.26

ObjectName

0.25

æĶ¾

0.25

åĮħ

0.25

pany

0.25

æŃĮè¯į

0.24

 Sting

0.24

Activations Density 0.034%

Nostalgia/memories

No Comments

No Known Activations