INDEX

Explanations

Random texts with punctuation

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

ublic

-0.25

è¿Ļæĸ¹éĿ¢

-0.24

æ¾İæ¹ĥ

-0.24

ħ§

-0.24

’e

-0.23

izio

-0.23

æī¹ç¤º

-0.23

iable

-0.23

ĪæĿĥ

-0.23

 ****************************************************************

-0.23

POSITIVE LOGITS

é¦Ļ

0.27

sid

0.27

ä¼´

0.27

åĨł

0.27

 increment

0.27

earer

0.26

çĨŁæĤī

0.25

ä¼ĺ

0.25

é«»

0.25

rem

0.25

Activations Density 1.812%

Random texts with punctuation

No Comments

No Known Activations