INDEX

Explanations

.

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_12.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.12.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pos

-0.29

 Limits

-0.27

éĻĲåº¦

-0.26

å¤Ķ

-0.26

åİ¿éķ¿

-0.26

-follow

-0.25

åĮ£

-0.25

 modes

-0.25

ä¸ĭä¹¡

-0.24

gars

-0.24

POSITIVE LOGITS

gtest

0.26

ren

0.26

ileen

0.25

lace

0.25

 chess

0.25

éĹ²

0.24

çĽĨ

0.24

 Moves

0.24

iesel

0.24

aoke

0.23

Activations Density 0.029%

.

No Comments

No Known Activations