INDEX

Explanations

federal

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icl

-0.29

hus

-0.26

 Ventura

-0.26

åºĬä¸Ĭ

-0.25

çĶ¨å¿ĥ

-0.25

åĲ¯

-0.24

 Closure

-0.24

lab

-0.24

 å·

-0.24

 killers

-0.24

POSITIVE LOGITS

åħ¬ä¼Ĺ

0.28

 relegated

0.26

åĪ°æĿ¥

0.25

æĶ¾åĩº

0.25

}`).

0.24

GetString

0.24

åľ¨è¿Ļä¸ª

0.24

>").

0.24

æĹ¶ä»£çļĦ

0.24

åĨ³

0.24

Activations Density 0.003%

federal

No Comments

No Known Activations