INDEX

Explanations

Glover

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

-strokes

-0.26

Caj

-0.26

eking

-0.26

wipe

-0.25

zens

-0.25

partner

-0.25

backs

-0.24

äººéĥ½

-0.24

ãģĮãģĭãģĭ

-0.23

 Celsius

-0.23

POSITIVE LOGITS

anter

0.27

 express

0.26

 adaptive

0.25

åĲŃ

0.24

é©¬æĿ¥

0.24

çļĦä¸ĢåĪĩ

0.24

ish

0.24

adaptive

0.23

ä¹ł

0.23

èĨĽ

0.23

Activations Density 7.617%

Glover

No Comments

No Known Activations