INDEX

Explanations

the

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĪĳè¯´

-0.29

ntag

-0.27

.lastIndexOf

-0.27

<object

-0.26

æĪĳçľŁçļĦ

-0.26

æĪĳæĬĬ

-0.25

steam

-0.24

ä¸ľè¥¿

-0.24

å½¹

-0.24

 fine

-0.24

POSITIVE LOGITS

*sin

0.26

 Quotes

0.25

hev

0.24

LEG

0.23

SCI

0.23

QUOTE

0.23

 quotes

0.23

urette

0.23

agen

0.23

quotes

0.23

Activations Density 0.001%

the

No Comments

No Known Activations