INDEX

Explanations

Vapor/steam

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

zel

-0.27

 Reign

-0.27

nock

-0.26

])**

-0.26

æīĢä»¥ä»ĸ

-0.26

quirrel

-0.26

çļĦç²¾ç¥ŀ

-0.25

ongyang

-0.25

FPS

-0.25

RPG

-0.25

POSITIVE LOGITS

ary

0.32

ide

0.28

Pair

0.25

cke

0.25

é©¬æĭī

0.25

iddle

0.25

è³ª

0.24

 candidates

0.24

newInstance

0.24

WARE

0.24

Activations Density 0.015%

Vapor/steam

No Comments

No Known Activations