INDEX

Explanations

Lunch

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

 freely

-0.28

 semif

-0.27

burg

-0.27

FT

-0.26

-exclusive

-0.25

 plurality

-0.25

æİĺ

-0.24

	Output

-0.24

usage

-0.24

 Output

-0.24

POSITIVE LOGITS

/boot

0.31

 attended

0.27

 Boot

0.27

ATUS

0.26

å½ĵåį³

0.25

è¯Ńè¨Ģ

0.25

æİ¥æĶ¶

0.24

èī¯

0.24

 attends

0.24

Boot

0.24

Activations Density 0.100%

Lunch

No Comments

No Known Activations