INDEX

Explanations

Hyphens

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

 cover

-0.30

 major

-0.30

 covers

-0.28

 shrink

-0.28

hon

-0.28

è¦ĨçĽĸ

-0.28

çĽĸ

-0.28

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.28

?:

-0.28

 Cover

-0.28

POSITIVE LOGITS

ernote

0.26

DataMember

0.25

iros

0.25

ayah

0.25

pars

0.25

gist

0.25

omore

0.24

lical

0.24

IDD

0.24

Vu

0.24

Activations Density 0.035%

Hyphens

No Comments

No Known Activations