INDEX

Explanations

Mixed text and numbers

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

 Bangalore

-0.34

 Pradesh

-0.33

 Kerala

-0.32

utar

-0.30

 Delhi

-0.29

Vij

-0.28

 Chennai

-0.27

 Karnataka

-0.27

 Nadu

-0.27

erala

-0.27

POSITIVE LOGITS

 prem

0.26

ford

0.25

Ã©mon

0.25

icy

0.24

çº

0.24

èĢ³æľµ

0.24

 begr

0.24

 modest

0.23

agrams

0.23

 trans

0.23

Activations Density 1.240%

Mixed text and numbers

No Comments

No Known Activations