© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    say parents

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

    No Comments

    Negative Logits
    (Configuration
    -15.69
     Disc
    -15.56
    él
    -15.44
    generated
    -15.25
    emat
    -15.19
     disc
    -14.81
    -produ
    -14.69
     unprotected
    -14.63
    aneous
    -14.56
     producción
    -14.50
    POSITIVE LOGITS
    爸
    15.69
    [parent
    14.63
    家长
    14.38
    Parents
    14.31
    电视台
    14.19
    emies
    14.13
    插
    14.00
    收紧
    13.50
    爸妈
    13.50
     parental
    13.38
    Activations Density 0.120%

    No Known Activations