INDEX

Explanations

Non-natural language text

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

ä¾Ľç»Ļ

-0.30

ioso

-0.27

aiser

-0.26

à¹īà¸Ńà¸Ļ

-0.26

 Contract

-0.26

inges

-0.25

 Supply

-0.25

 trick

-0.25

éŀį

-0.25

 sensible

-0.24

POSITIVE LOGITS

<![

0.29

ANI

0.28

åĽº

0.27

ANE

0.26

.addView

0.25

åħ¨ä½ĵ

0.24

.viewer

0.24

èĬ¯

0.24

NZ

0.24

<![

0.24

Activations Density 0.018%

Non-natural language text

No Comments

No Known Activations