INDEX

Explanations

virus

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

itian

-0.27

asurer

-0.27

'field

-0.27

urious

-0.26

uels

-0.25

uations

-0.25

amide

-0.25

HCI

-0.25

uing

-0.25

atee

-0.25

POSITIVE LOGITS

éĿ¢å¯¹

0.31

æī¿

0.31

éĿ¢å°į

0.30

äºĽ

0.28

ä¼į

0.27

åĽ¢

0.26

åħ¸

0.26

æĭĽ

0.25

oun

0.25

 facing

0.25

Activations Density 0.049%

virus

No Comments

No Known Activations