© 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. 14747
    Prev
    Next
    INDEX
    Explanations

    say "3"

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

    No Comments

    Negative Logits
     shale
    -19.63
    科尔
    -19.25
    etre
    -18.00
    阿尔
    -17.88
    衬衫
    -17.75
    issippi
    -17.50
    コーヒー
    -17.50
    cala
    -17.25
     Sheriff
    -17.00
     CCP
    -17.00
    POSITIVE LOGITS
    ped
    16.63
    ток
    16.13
     ped
    15.50
    织
    14.63
    odom
    14.56
    PED
    14.44
    amentos
    13.88
    法定
    13.81
     Lud
    13.56
     provision
    13.50
    Activations Density 0.071%

    No Known Activations