© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15220
    Prev
    Next
    INDEX
    Explanations

    say "Indonesian/Malay"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getDb
    -18.38
    òn
    -17.88
    锌
    -16.75
     ozone
    -16.50
     Vaults
    -16.13
    ItemCount
    -15.88
    magnitude
    -15.69
    甥
    -15.56
     oz
    -15.38
    Winter
    -15.31
    POSITIVE LOGITS
     Indonesian
    33.25
     Malaysian
    31.50
     Malay
    31.13
     Malays
    30.63
     Indones
    30.25
     Malaysia
    29.38
     Indonesia
    28.38
    印尼
    26.75
     Kuala
    25.63
    马来
    24.75
    Activations Density 0.220%

    No Known Activations