INDEX

Explanations

ours

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stud

-0.28

KP

-0.27

maj

-0.26

 Life

-0.25

 Sheldon

-0.25

Life

-0.25

ÐµÐ±

-0.25

maj

-0.24

_ticks

-0.24

 panel

-0.24

POSITIVE LOGITS

ä¸įåĪ°

0.38

/libs

0.27

ifndef

0.27

 inventor

0.26

laus

0.26

ç»»

0.26

åħ¶éĹ´

0.25

-definition

0.24

æĪĳçİ°åľ¨

0.24

å¿ĺè®°

0.24

Activations Density 26.560%

ours

No Comments

No Known Activations