INDEX

Explanations

code or technical posts

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

egra

-0.32

Ħä»¶

-0.26

 pane

-0.25

-clock

-0.25

autorelease

-0.25

scape

-0.25

pane

-0.24

 Plastic

-0.24

 REPLACE

-0.24

cope

-0.23

POSITIVE LOGITS

æĮĳ

0.27

ä»ĩ

0.26

åĦ²

0.25

ä»ĵåĤ¨

0.25

ä¸Ģåı£

0.25

å¿Ĺ

0.25

ä¾¿åı¯

0.24

[,

0.24

 exercised

0.24

é¡¹éĵ¾

0.24

Activations Density 0.000%

code or technical posts

No Comments

No Known Activations