INDEX

Explanations

code and data manipulation

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

ä¼ļè®©ä½ł

-0.26

åĤ¬

-0.25

æ©Ľ

-0.24

-direct

-0.24

éĩįå»º

-0.23

 separ

-0.23

structuring

-0.23

èĢĮéĿŀ

-0.23

taÅĤ

-0.23

è¿Ļä¹Ī

-0.23

POSITIVE LOGITS

Sharp

0.28

lescope

0.28

aser

0.27

flate

0.26

BarController

0.26

 Sharp

0.26

å®ŀéĻħæĥħåĨµ

0.26

igram

0.26

ħĮ

0.25

sections

0.25

Activations Density 0.104%

code and data manipulation

No Comments

No Known Activations