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

    Neuronpedia

    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. 15594
    Prev
    Next
    INDEX
    Explanations

    name completion

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

    No Comments

    Negative Logits
    qd
    -28.38
     QU
    -26.88
    quo
    -26.25
    qu
    -25.50
    _qu
    -25.25
    Qu
    -25.13
     QS
    -24.63
     Qu
    -24.50
    QS
    -24.50
    .qu
    -24.38
    POSITIVE LOGITS
     lsp
    18.50
     sperm
    18.13
    吹
    17.50
    麻醉
    17.25
     Devil
    17.13
     esp
    16.75
     condom
    16.63
    獠
    16.38
     contraceptive
    16.38
    -dr
    16.38
    Activations Density 0.848%

    No Known Activations