INDEX

Explanations

Names/name parts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

raith

-0.28

á»¦

-0.27

typeid

-0.25

iggins

-0.25

åģ¥èº«

-0.24

èį¡

-0.24

ãģ«è¡Įãģ£ãģ¦

-0.24

avana

-0.24

izzlies

-0.24

åı¯è¡ĮæĢ§

-0.24

POSITIVE LOGITS

.draw

0.29

ä¹ĭä½Ļ

0.28

phia

0.28

 draw

0.25

åħĪéĶĭ

0.25

åı¦ä¸Ģæĸ¹éĿ¢

0.25

 eventual

0.24

PH

0.24

 regions

0.24

.exit

0.23

Activations Density 0.002%

Names/name parts

No Comments

No Known Activations