INDEX

Explanations

Questions and answers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ¯ģ

-0.29

rott

-0.28

é¢ĺ

-0.27

 altogether

-0.27

æĪĳä»¬å°±

-0.26

çģ¾

-0.25

amat

-0.25

egov

-0.25

Lo

-0.24

argin

-0.24

POSITIVE LOGITS

çĮ¬

0.29

ewing

0.28

lint

0.27

 jump

0.26

 maximize

0.24

 princip

0.24

hor

0.24

é¹ĺ

0.24

 dÃ©marche

0.24

 Naked

0.23

Activations Density 0.021%

Questions and answers

No Comments

No Known Activations