INDEX

Explanations

way

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

 plat

-0.29

æĹ¥æĻļéĹ´

-0.27

æ·¹

-0.27

å¼¥

-0.26

é¡µ

-0.26

 plates

-0.26

 margin

-0.26

éķ£

-0.26

umat

-0.25

Library

-0.25

POSITIVE LOGITS

sse

0.28

dl

0.25

 guaranteed

0.25

igne

0.25

.tolist

0.24

hare

0.24

ane

0.23

Ð±Ð°Ð»

0.23

 Guaranteed

0.23

dbe

0.23

Activations Density 0.018%

way

No Comments

No Known Activations