INDEX

Explanations

forces

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

 forces

-0.29

 Powers

-0.28

 autor

-0.26

forces

-0.25

 powers

-0.25

 custody

-0.25

çĤ

-0.25

 persons

-0.25

 softly

-0.25

 abstract

-0.24

POSITIVE LOGITS

åĪ©

0.29

åĦ¿

0.28

asca

0.28

.FILL

0.25

èĪŀ

0.25

ÐµÐ½ÑĮ

0.24

 dime

0.24

åŀĭä¼ģä¸ļ

0.24

divide

0.24

subs

0.24

Activations Density 0.244%

forces

No Comments

No Known Activations