INDEX

Explanations

research and experiments

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

 sample

-0.32

 sampling

-0.31

 samples

-0.29

 Sampling

-0.28

 microbial

-0.27

 recon

-0.27

sample

-0.26

 Sample

-0.26

-sample

-0.26

æł·æľ¬

-0.26

POSITIVE LOGITS

atica

0.29

è£

0.28

å®īåħ¨æĦŁ

0.27

æŃĮ

0.27

åłĨ

0.26

æİİ

0.25

ç¿ķ

0.25

abar

0.25

æĶĺ

0.24

åĽ½åĢº

0.24

Activations Density 0.039%

research and experiments

No Comments

No Known Activations