INDEX

Explanations

code and documentation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¹īà¸Ńà¸Ļ

-0.30

åħ¥èĤ¡

-0.30

idor

-0.26

 láº¯m

-0.26

WithOptions

-0.25

åľºä¸Ĭ

-0.25

å°¤ä¸ºéĩįè¦ģ

-0.24

é«ĺåİŁ

-0.24

offer

-0.24

å¾ĭ

-0.24

POSITIVE LOGITS

æĬĢ

0.26

 prefect

0.26

éĢ®

0.26

 tÆ°á»Ľng

0.26

SAN

0.25

 consult

0.25

ABCDEFG

0.25

src

0.25

 average

0.24

*x

0.24

Activations Density 0.081%

code and documentation

No Comments

No Known Activations