INDEX

Explanations

code snippets/syntax

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

ç©ºæ°Ķ

-0.28

 ceilings

-0.26

 indirect

-0.26

ç©ºæ°Ķè´¨éĩı

-0.25

air

-0.24

-friendly

-0.24

éĺ²ç©º

-0.24

æľĢéļ¾

-0.24

ä¸įå®¹æĺĵ

-0.24

ental

-0.23

POSITIVE LOGITS

Ð½Ð¸Ð¸

0.30

 Incre

0.29

iard

0.29

 Spread

0.28

{text

0.27

 Printing

0.26

ç¾Ķ

0.26

tfoot

0.26

inia

0.25

ä¸įæŃ»

0.25

Activations Density 0.003%

code snippets/syntax

No Comments

No Known Activations