INDEX

Explanations

,

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

izin

-0.27

vim

-0.25

à¸ĩ

-0.25

æľ¬äºº

-0.25

åĲĮçŃī

-0.24

/frontend

-0.24

èĥĮéĥ¨

-0.23

.backend

-0.23

adio

-0.23

ç¦ıéŁ³

-0.23

POSITIVE LOGITS

åŀĥåľ¾åĪĨç±»

0.39

 recycl

0.30

æ±¡æ³¥

0.30

çĦļçĥ§

0.30

 trash

0.28

 sanitation

0.28

Bins

0.28

engers

0.28

åŀĥåľ¾æ¡¶

0.28

 landfill

0.27

Activations Density 0.052%

,

No Comments

No Known Activations