INDEX

Explanations

hypertension

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

å¾Ħ

-0.31

neas

-0.28

 ground

-0.28

å¾ĳ

-0.27

DER

-0.25

.–

-0.24

éĿ¢

-0.24

ä¹ĭå®¶

-0.24

ç¦»

-0.24

TAIL

-0.24

POSITIVE LOGITS

ObjectContext

0.28

åįĩéĻį

0.27

ç¢ĳ

0.26

éĹ¿

0.24

 unst

0.24

DataContext

0.24

WindowText

0.24

Saint

0.24

 prejud

0.24

cura

0.23

Activations Density 30.386%

hypertension

No Comments

No Known Activations