INDEX

Explanations

Article/blog post excerpts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 onFailure

-0.28

ç±»ä¼¼çļĦ

-0.27

SQL

-0.26

AsyncResult

-0.25

äº§ä¸ļåŁºåľ°

-0.24

ikes

-0.24

.SQL

-0.23

DEX

-0.23

RX

-0.23

 unintention

-0.23

POSITIVE LOGITS

ipop

0.29

roots

0.28

 firing

0.27

åıĳåĩº

0.26

 roots

0.25

é©¾

0.25

ç³

0.24

ÐºÐ¾Ð»ÑĮ

0.24

cala

0.24

typings

0.24

Activations Density 0.820%

Article/blog post excerpts

No Comments

No Known Activations