INDEX

Explanations

with

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

å®ŀéªĮå®¤

-0.27

ksam

-0.26

 experiments

-0.24

DIFF

-0.24

 inhal

-0.24

çªĴ

-0.24

ÙĥØ³Ø¨

-0.24

-fetch

-0.24

 investig

-0.24

è¯ķéªĮ

-0.24

POSITIVE LOGITS

æĢģåĬ¿

0.30

romatic

0.28

 datastore

0.27

orp

0.27

èĽİ

0.26

æĺİ

0.25

æĢ»å±Ģ

0.25

ç»¼åĲĪæ²»çĲĨ

0.25

æĿ¥çĶµ

0.25

 Civilization

0.24

Activations Density 0.019%

with

No Comments

No Known Activations