© 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. 14905
    Prev
    Next
    INDEX
    Explanations

    N/A

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

    No Comments

    Negative Logits
    еле
    -21.13
    eda
    -20.88
    sed
    -20.00
    elle
    -20.00
     Dee
    -19.88
    oble
    -19.63
    eel
    -19.13
     Kel
    -18.88
    elay
    -18.75
    pee
    -18.75
    POSITIVE LOGITS
     sinc
    18.63
     vic
    17.50
    ymi
    16.25
    ustin
    15.88
    弇
    15.75
    ZN
    15.44
    ught
    15.38
    ハン
    15.31
    .Sync
    15.31
    horn
    15.25
    Activations Density 1.065%

    No Known Activations