INDEX

Explanations

most

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

)?$

-0.25

NEG

-0.25

æľĢè¿ĳ

-0.25

 Recent

-0.24

Director

-0.24

mpl

-0.24

 IsValid

-0.24

 recent

-0.24

recent

-0.24

uber

-0.23

POSITIVE LOGITS

elian

0.28

ifik

0.27

elda

0.26

.setModel

0.26

nets

0.25

Shar

0.25

azaar

0.25

uchsia

0.24

elines

0.24

antly

0.24

Activations Density 30.902%

most

No Comments

No Known Activations