INDEX

Explanations

period

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĳµ

-0.30

tail

-0.29

:Event

-0.28

 tail

-0.26

 RELATED

-0.26

æĤī

-0.26

CodeAt

-0.26

bread

-0.25

ç»¼åĲĪåĪ©çĶ¨

-0.25

abez

-0.24

POSITIVE LOGITS

 Pods

0.27

atives

0.27

etest

0.26

ajor

0.25

åĬ«

0.24

æµ·å³¡

0.24

)','

0.24

thon

0.24

atform

0.23

licht

0.23

Activations Density 0.406%

period

No Comments

No Known Activations