INDEX

Explanations

Non-simple English text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nos

-0.28

 real

-0.28

 independent

-0.27

ga

-0.27

 other

-0.27

baugh

-0.27

 reverse

-0.27

å®ŀ

-0.27

burgh

-0.27

POSITIVE LOGITS

ylene

0.30

orny

0.27

ç¨ħ

0.26

çº¢æĺŁ

0.26

Ã¨ne

0.25

.btnCancel

0.25

 Sport

0.25

æĺĤè´µ

0.25

Sport

0.24

çļĦä¸Ģåĳĺ

0.24

Activations Density 0.029%

Non-simple English text

No Comments

No Known Activations