INDEX

Explanations

Angular scope

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

Kem

-0.27

ä¹¦è®°

-0.27

stamp

-0.25

æī£

-0.25

Lat

-0.25

era

-0.25

Stamp

-0.25

à¸¥à¸³

-0.25

å¡Ķ

-0.25

icode

-0.24

POSITIVE LOGITS

scope

0.40

	scope

0.38

 scope

0.38

.Scope

0.38

ng

0.37

 directive

0.35

Ctrl

0.35

 directives

0.34

(scope

0.34

 Scope

0.33

Activations Density 0.099%

Angular scope

No Known Activations