INDEX

Explanations

Luc

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

å¡ĺ

-0.25

developer

-0.25

å¼Ģåıĳå»ºè®¾

-0.25

å¼ĢåıĳåķĨ

-0.25

 broad

-0.25

lam

-0.25

é¢Ĺ

-0.24

æ®µæĹ¶éĹ´

-0.24

èķī

-0.24

moth

-0.24

POSITIVE LOGITS

 hole

0.29

hole

0.27

pud

0.27

æīįåı¯ä»¥

0.26

LEG

0.26

æ©Ľ

0.25

ä¸įèĤ¯

0.25

å²ģä»¥ä¸Ĭ

0.24

_void

0.24

 cutter

0.24

Activations Density 1.325%

Luc

No Comments

No Known Activations