INDEX

Explanations

Mixed excerpts and unusual formatting

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

ipi

-0.30

åİ¢

-0.26

dig

-0.26

ocene

-0.25

inf

-0.25

 aÃ±

-0.25

geries

-0.25

omed

-0.25

ipop

-0.25

 reel

-0.24

POSITIVE LOGITS

å°ĳ

0.28

èħ¥

0.27

blings

0.26

å¤ļä½Ļ

0.25

ÑĢÐ°Ð¶

0.24

é¢Ŀ

0.24

hammer

0.24

Ä±l

0.24

å®ªæ³ķ

0.24

æī¹åıĳ

0.23

Activations Density 0.062%

Mixed excerpts and unusual formatting

No Comments

No Known Activations