INDEX

Explanations

Code and technical content

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

orny

-0.30

/twitter

-0.29

è¡®

-0.28

ä¸ĵäº«

-0.27

 Flour

-0.27

apy

-0.26

ãģĵãģ¨ãĤĤ

-0.26

èĢģäººå®¶

-0.25

åħ¨å¹´

-0.25

atism

-0.24

POSITIVE LOGITS

ç»Ħ

0.29

ling

0.29

éĥ¨

0.27

èģª

0.26

 Lakes

0.26

 anthrop

0.25

çµĦ

0.25

Generic

0.25

 soph

0.25

à´Ļ

0.25

Activations Density 0.722%

Code and technical content

No Comments

No Known Activations