INDEX

Explanations

est

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

è¡¨çİ°

-0.27

iou

-0.25

çĺ«

-0.25

summ

-0.25

escription

-0.25

uctions

-0.24

 Recipes

-0.23

ReturnValue

-0.23

æĢ»ç»ĵ

-0.23

 Spot

-0.23

POSITIVE LOGITS

riter

0.28

Ã³g

0.27

 modular

0.26

æ¨¡åĿĹ

0.26

çī¹æĸ¯

0.26

aremos

0.25

 []:↵

0.25

%</

0.25

ä¹īä¹Į

0.25

 Modular

0.25

Activations Density 0.031%

est

No Comments

No Known Activations