INDEX

Explanations

Software development

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

åģļäºº

-0.32

éĴŀ

-0.32

çļĦå¿ĥæĥħ

-0.28

wh

-0.27

ubo

-0.27

æ³¼

-0.26

ä»½

-0.26

AUX

-0.26

cling

-0.26

.Companion

-0.25

POSITIVE LOGITS

 Invasion

0.27

ä¸ŃåİŁ

0.27

dispatch

0.26

Ä«

0.25

 Insets

0.25

ittings

0.24

å´©

0.24

ournals

0.23

abb

0.23

è°ĥéħį

0.23

Activations Density 0.009%

Software development

No Comments

No Known Activations