INDEX

Explanations

opian

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

 Ital

-0.28

çŁ³èĨı

-0.25

åĨįåĬłä¸Ĭ

-0.25

åħ¥å¢ĥ

-0.25

æĥŁ

-0.24

å³¡

-0.24

unde

-0.24

orda

-0.24

uese

-0.23

 æı

-0.23

POSITIVE LOGITS

 Vend

0.28

jsc

0.27

 donors

0.26

Crow

0.25

 hang

0.25

 turbines

0.24

apa

0.24

 crowdfunding

0.24

pou

0.24

\Resources

0.24

Activations Density 1.081%

opian

No Comments

No Known Activations