© 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. 14399
    Prev
    Next
    INDEX
    Explanations

    letter V

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

    No Comments

    Negative Logits
    aida
    -21.63
    aisy
    -21.25
    エル
    -21.13
     cud
    -20.50
    adow
    -20.38
    dart
    -20.13
    adero
    -20.00
     Sanders
    -19.88
    cycl
    -19.88
     Alic
    -19.75
    POSITIVE LOGITS
    sembl
    12.94
    col
    12.94
     Col
    12.81
    umes
    12.44
    U
    12.31
    ù
    12.25
    约合
    12.13
    var
    12.06
    赃
    11.69
     col
    11.63
    Activations Density 0.009%

    No Known Activations