INDEX

Explanations

hey

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

 wast

-0.28

PERT

-0.28

åį´è¢«

-0.27

 dÃ©march

-0.27

opyright

-0.26

èĩªä¸»åĵģçīĮ

-0.26

]];

-0.25

]];

-0.25

åĲĪæ³ķ

-0.25

dru

-0.24

POSITIVE LOGITS

oring

0.26

çĿĽ

0.25

 storing

0.25

arching

0.25

 concentrating

0.24

ëģ¼

0.24

ç»»

0.24

æľĭåıĭä»¬

0.23

URE

0.23

rias

0.23

Activations Density 0.003%

hey

No Comments

No Known Activations