© 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. 14434
    Prev
    Next
    INDEX
    Explanations

    say 2

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

    No Comments

    Negative Logits
     Tango
    -25.50
     Tanz
    -23.00
     Ranger
    -20.63
     Paige
    -20.25
    (Parcel
    -19.63
     Ranch
    -19.13
     Mang
    -18.88
     Lal
    -18.88
     muff
    -18.75
    アン
    -18.75
    POSITIVE LOGITS
    oke
    16.75
    耀
    13.94
    oric
    13.81
    垚
    13.69
     heav
    13.69
    y
    13.69
    金色
    13.69
    重度
    13.38
    ork
    13.25
    沉
    13.19
    Activations Density 0.126%

    No Known Activations