INDEX

Explanations

ing

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

rfl

-0.26

mary

-0.25

.lr

-0.25

.Deserialize

-0.24

.getAs

-0.24

ä¸ĭæ²ī

-0.24

rella

-0.23

asString

-0.23

æ³ħ

-0.23

åħ¨æ°ĳåģ¥èº«

-0.23

POSITIVE LOGITS

æī¹è¯Ħ

0.31

zan

0.28

ataka

0.27

ominated

0.27

åĪĩæĪĲ

0.25

äºĭåĬ¡

0.24

/controllers

0.24

cz

0.24

åº§ä½į

0.24

QC

0.24

Activations Density 0.005%

ing

No Comments

No Known Activations