INDEX

Explanations

if

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

obox

-0.30

PTR

-0.26

Father

-0.25

ç¼ķ

-0.25

bars

-0.25

æķ²

-0.24

 oppos

-0.24

 pointed

-0.24

wards

-0.24

 drum

-0.24

POSITIVE LOGITS

ä½ľèĢħæľ¬äºº

0.28

ecret

0.26

actual

0.25

 Polo

0.25

Secret

0.24

olf

0.24

.initializeApp

0.24

alem

0.24

enuine

0.24

achi

0.23

Activations Density 0.039%

if

No Comments

No Known Activations