INDEX

Explanations

of

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

 Charter

-0.28

Cal

-0.28

rael

-0.27

Cal

-0.27

 dere

-0.27

cal

-0.26

Net

-0.26

 Couch

-0.26

iron

-0.26

 Bass

-0.25

POSITIVE LOGITS

ducted

0.31

platz

0.27

ewis

0.26

ainer

0.26

intptr

0.25

 redraw

0.25

andel

0.25

aked

0.25

lover

0.24

æĭĽ

0.24

Activations Density 0.405%

of

No Comments

No Known Activations