© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14308
    Prev
    Next
    INDEX
    Explanations

    say spray

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

    No Comments

    Negative Logits
    _PARSE
    -17.63
    建设工程
    -16.63
    ilia
    -16.13
    建设项目
    -15.69
    蒐集
    -15.50
    (Parse
    -15.50
    (policy
    -15.38
    隈
    -15.38
    羡慕
    -15.31
    掇
    -15.31
    POSITIVE LOGITS
     sprayed
    26.75
    喷
    26.38
     spray
    25.63
     spraying
    25.25
     spr
    24.50
     Spray
    21.63
    噴
    21.50
    spr
    21.38
     application
    21.13
    Spr
    20.75
    Activations Density 0.341%

    No Known Activations