INDEX

Explanations

low

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

ÑĤÐ°Ð¹

-0.28

opal

-0.24

omination

-0.24

 deserve

-0.24

è¡¨æĥħ

-0.24

ä½¿ä¹ĭ

-0.24

åºıåĪĹ

-0.24

lay

-0.24

 sequence

-0.24

Standing

-0.23

POSITIVE LOGITS

 humanity

0.26

åĭĴ

0.26

èĥĦ

0.25

åĭĺ

0.25

 onNext

0.24

åľ¨è¿ĩæ¸¡

0.23

 iÃ§erisinde

0.23

shaw

0.23

æ±ĩéĽĨ

0.23

å¾Ĵå¼Ł

0.23

Activations Density 0.003%

low

No Comments

No Known Activations