INDEX

Explanations

code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ons

-0.26

ER

-0.26

åħµ

-0.25

à¹Ĩ

-0.25

otto

-0.25

TR

-0.25

 à¹Ĩ

-0.24

UT

-0.24

è¾¹

-0.24

ä¸Ģèµ·

-0.24

POSITIVE LOGITS

æĥ³æī¾

0.30

è¿Ļä¸ªæĹ¶åĢĻ

0.28

éĤ£ä¸ĢåĪ»

0.27

.NewReader

0.27

echa

0.26

å°±è§īå¾Ĺ

0.26

åľ¨åĲĮä¸Ģ

0.26

ÑĨÐ¸Ð¿

0.25

éĤ£ä¸ªæĹ¶åĢĻ

0.25

rix

0.25

Activations Density 0.021%

code

No Comments

No Known Activations