INDEX

Explanations

encouraging and support

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

-origin

-0.29

à¹Ĥà¸ķ

-0.27

åĲ¹

-0.26

ç¬ĥ

-0.25

bout

-0.25

.boost

-0.24

æ²½

-0.23

-lite

-0.23

 connected

-0.23

 lifted

-0.23

POSITIVE LOGITS

edian

0.29

ÑĢÑĥÑĤ

0.26

ead

0.24

ä½ķ

0.24

æ¸©

0.23

 Braz

0.23

 brides

0.23

è´«

0.23

rend

0.23

.Css

0.23

Activations Density 0.401%

encouraging and support

No Known Activations