INDEX

Explanations

Questions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç¬¬ä¸ĢæĿ¡

-0.27

åį´æĺ¯

-0.25

iÃ¨rement

-0.24

itize

-0.24

çº½

-0.24

nowled

-0.24

Pinterest

-0.24

uarios

-0.24

ÃŃtulo

-0.23

panse

-0.23

POSITIVE LOGITS

æĢİä¹ĪåĬŀ

0.32

éĬ·

0.27

 Heck

0.26

éĶĢ

0.25

æķ£åıĳ

0.25

aside

0.25

ä¸ĭæ²ī

0.24

ÙĦÙĥ

0.24

 aside

0.24

æĮº

0.24

Activations Density 0.001%

Questions

No Comments

No Known Activations