INDEX

Explanations

court

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

uards

-0.30

æĭŃ

-0.28

dor

-0.27

mnt

-0.26

rstrip

-0.26

éĢļãĤĬ

-0.25

ç¢°æĴŀ

-0.24

(dp

-0.24

 rainfall

-0.24

äººæł¼

-0.24

POSITIVE LOGITS

å®ª

0.28

tery

0.27

eldon

0.27

¬´

0.25

aber

0.25

æķĽ

0.24

FACE

0.24

intage

0.24

 Friedman

0.24

Activations Density 0.010%

court

No Comments

No Known Activations