INDEX

Explanations

Code and technical documentation

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

æĬĽå¼ĥ

-0.29

olan

-0.28

rer

-0.28

åŃ½

-0.27

berry

-0.27

éĻį

-0.25

å¼ĥ

-0.24

æ·¡åĮĸ

-0.24

 riches

-0.24

bots

-0.24

POSITIVE LOGITS

Ã§o

0.31

urette

0.28

etically

0.26

çķļ

0.25

pline

0.25

inke

0.25

ernes

0.24

-limit

0.24

DataContext

0.24

 letter

0.24

Activations Density 0.009%

Code and technical documentation

No Comments

No Known Activations