INDEX

Explanations

metrics

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

ANCH

-0.30

'~/

-0.29

adero

-0.27

éļ¾çĤ¹

-0.26

åħ±åĲĮåıĳå±ķ

-0.26

ç¤¼æĭľ

-0.25

å·²ä¹ħçļĦ

-0.25

åĮĹæµ·

-0.25

anch

-0.24

uddy

-0.24

POSITIVE LOGITS

.Distance

0.34

 Promise

0.28

çĽı

0.27

ç´§

0.25

éģį

0.25

lide

0.25

ä¾Ŀèµĸ

0.25

ä¾Ŀ

0.25

 Sense

0.25

è¡¡éĩı

0.24

Activations Density 15.664%

metrics

No Comments

No Known Activations