INDEX

Explanations

Names or organizations

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

endo

-0.28

irlines

-0.26

odable

-0.26

UCE

-0.26

precation

-0.25

 breast

-0.25

USES

-0.25

ÑģÑĤÑĮ

-0.24

ä¹¦è®°

-0.24

egra

-0.24

POSITIVE LOGITS

ç»§

0.27

router

0.26

Io

0.26

åıł

0.25

wym

0.24

áĢĬ

0.24

åħ´

0.23

æ£º

0.23

ç³Ĭ

0.23

oly

0.23

Activations Density 0.023%

Names or organizations

No Comments

No Known Activations