INDEX

Explanations

all

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

 Cheney

-0.29

DK

-0.26

åħį

-0.26

Emm

-0.25

ril

-0.25

inet

-0.25

GK

-0.24

 dÆ°á»¡ng

-0.24

FileNotFoundException

-0.24

 Katy

-0.23

POSITIVE LOGITS

smith

0.28

STRUCTIONS

0.26

ç½ħ

0.26

ucher

0.25

.codes

0.25

ciÃ³

0.25

armed

0.25

apest

0.24

è¾ī

0.24

paces

0.24

Activations Density 0.005%

all

No Comments

No Known Activations