INDEX

Explanations

genetics and heredity

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¶Ī

-0.28

_elim

-0.26

è¢«åĬ¨

-0.24

æĬł

-0.24

äºĨå¤ļå°ĳ

-0.24

.vol

-0.23

Regs

-0.23

ê±°

-0.23

 Faul

-0.23

çĺ«

-0.23

POSITIVE LOGITS

 inheritance

0.32

 genetic

0.31

 inher

0.31

 inherited

0.30

 carrier

0.29

 inherits

0.28

 inherit

0.28

 advice

0.27

.advance

0.27

Carrier

0.27

Activations Density 0.161%

genetics and heredity

No Comments

No Known Activations