INDEX

Explanations

in

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

_hour

-0.26

èŁ¾

-0.25

 Feature

-0.24

è¢Ń

-0.24

_hor

-0.23

 Nguy

-0.23

 feature

-0.23

è®®

-0.23

imoto

-0.23

æļĹ

-0.23

POSITIVE LOGITS

ople

0.29

 undo

0.28

junction

0.27

 ware

0.26

çļĦæľĢå¤§

0.26

_WP

0.26

undo

0.25

æ¹ĸæ³Ĭ

0.25

oppable

0.25

çķĪ

0.25

Activations Density 0.007%

in

No Comments

No Known Activations