INDEX

Explanations

few

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

æĦĪ

-0.27

ass

-0.27

ffield

-0.26

 trick

-0.25

 arrayOf

-0.25

elay

-0.25

è¹ļ

-0.24

à¦«

-0.24

rer

-0.24

attle

-0.24

POSITIVE LOGITS

UCH

0.26

ÑĢÐ°Ð¹

0.26

chw

0.25

UU

0.25

è¾Ľ

0.25

æµ´å®¤

0.25

æ³¨æĦıåĪ°

0.24

 zich

0.24

 Chip

0.24

ä¹Łä¸įä¾ĭå¤ĸ

0.23

Activations Density 0.024%

few

No Comments

No Known Activations