INDEX

Explanations

for

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zew

-0.30

Automatic

-0.28

umeric

-0.27

åĲĮæ¯Ķä¸ĭéĻį

-0.26

 lowes

-0.25

utos

-0.25

å¤įä¹ł

-0.25

 Automatic

-0.24

aut

-0.24

ein

-0.24

POSITIVE LOGITS

izedName

0.28

æİīäºĨ

0.27

èį·

0.26

èĲģ

0.25

æĶ¹åıĺäºĨ

0.25

æīĵæĸŃ

0.25

itol

0.25

 reloc

0.24

çŃ¾è®¢äºĨ

0.24

è°ĥ

0.24

Activations Density 0.005%

for

No Comments

No Known Activations