INDEX

Explanations

Technical and code-related texts

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

éĢĶä¸Ń

-0.28

felt

-0.27

ods

-0.27

issors

-0.26

 holds

-0.26

 Wage

-0.26

arg

-0.25

ç¥ŀç§ĺ

-0.25

sek

-0.25

å³Ń

-0.25

POSITIVE LOGITS

Ð½Ð¾ÑģÑĤ

0.27

nell

0.26

avra

0.25

",-

0.25

agram

0.24

æļ

0.24

",__

0.24

 Lawrence

0.24

omba

0.24

ordes

0.23

Activations Density 0.005%

Technical and code-related texts

No Comments

No Known Activations