INDEX

Explanations

comma

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

åĲĦæł·

-0.27

 particular

-0.27

çī¹å®ļ

-0.27

imiento

-0.25

ids

-0.25

urrent

-0.24

äº

-0.24

å±ĭåŃĲ

-0.24

iders

-0.24

ury

-0.24

POSITIVE LOGITS

arella

0.26

sell

0.25

çķħéĶĢ

0.24

=params

0.24

 exon

0.24

 Phillips

0.24

gene

0.23

à¹Ģà¸ŀà¸¥à¸ĩ

0.23

ç¢İ

0.23

ise

0.23

Activations Density 0.019%

comma

No Comments

No Known Activations