INDEX

Explanations

Alerts and system messages

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.',č↵

-0.29

ONO

-0.29

.':

-0.27

ï¼ļ</

-0.27

:';↵

-0.27

ãĢĤ</

-0.27

ï¼ģ");↵

-0.26

 ventil

-0.26

ithmetic

-0.26

.');č↵

-0.26

POSITIVE LOGITS

éĵ¾æİ¥

0.28

Co

0.26

 Copies

0.26

FL

0.26

 Related

0.26

Dec

0.26

ä¸Ģä»½

0.26

Related

0.25

Fl

0.25

Co

0.24

Activations Density 0.016%

Alerts and system messages

No Comments

No Known Activations