INDEX

Explanations

long

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

ItemImage

-0.30

Ð´Ð²

-0.25

æľºæ²¹

-0.25

{"

-0.25

 smoke

-0.24

 smoking

-0.24

æĶ¯è¡Į

-0.24

æĸ°åŁİ

-0.24

æİĴæ±¡

-0.24

æĹĭ

-0.24

POSITIVE LOGITS

bsites

0.31

jong

0.28

ucceeded

0.26

DONE

0.25

çĻ¾å®¶

0.25

éĵ¯

0.24

yped

0.24

Tiles

0.24

 empower

0.23

èĽĻ

0.23

Activations Density 0.026%

long

No Comments

No Known Activations