INDEX

Explanations

Code and legal disclaimers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

endpoint

-0.29

curr

-0.26

èĪ«

-0.25

 endpoints

-0.25

 endpoint

-0.25

 originally

-0.24

 Wings

-0.24

/bg

-0.24

 æĢ

-0.24

åģĥ

-0.24

POSITIVE LOGITS

EMA

0.27

ä¸ĭéĿ¢æĺ¯å°ı

0.27

·»

0.25

 heavier

0.25

["+

0.25

Ð½Ð¸ÑĨ

0.25

 weighed

0.24

phetamine

0.24

 setSupportActionBar

0.24

ILog

0.24

Activations Density 0.012%

Code and legal disclaimers

No Comments

No Known Activations