© 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. 14370
    Prev
    Next
    INDEX
    Explanations

    say Kennedy

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

    No Comments

    Negative Logits
     models
    -19.00
    .models
    -18.88
     Modeling
    -18.75
    モデル
    -18.50
    models
    -18.50
     Models
    -18.25
    Models
    -18.13
     модель
    -17.88
    模型
    -17.88
    modele
    -17.75
    POSITIVE LOGITS
    айл
    16.00
    elog
    15.00
    htag
    14.88
    alc
    14.69
    atches
    14.13
    alog
    14.00
    alic
    13.56
    imary
    13.25
    ToAdd
    13.19
     external
    13.06
    Activations Density 0.010%

    No Known Activations