© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3156
    Prev
    Next
    INDEX
    Explanations

    say model

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     part
    -16.38
     Part
    -14.06
    (part
    -13.44
    =item
    -13.38
    GOR
    -13.31
    ped
    -13.13
    Part
    -13.06
     Ped
    -13.00
     Ring
    -13.00
     ped
    -12.94
    POSITIVE LOGITS
    车型
    22.75
     modele
    21.00
    $model
    18.25
    模型
    18.25
     getModel
    18.13
     vehicles
    17.88
     models
    17.88
    getModel
    17.75
    MessageType
    17.75
    ryo
    17.38
    Activations Density 0.036%

    No Known Activations