INDEX

Explanations

the

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

 automation

-0.32

 Province

-0.30

 blessing

-0.30

 automated

-0.29

 automate

-0.28

MainMenu

-0.28

ä¸ĢéĶ®

-0.27

 Automation

-0.27

elic

-0.27

automation

-0.27

POSITIVE LOGITS

ä»·

0.28

æĹłåģ¿

0.27

KP

0.26

onis

0.26

_KP

0.26

Ð¸ÑĪ

0.25

 Gang

0.25

ffi

0.25

åĲ«

0.24

æķ´çĲĨ

0.24

Activations Density 1.755%

the

No Comments

No Known Activations