© 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. 14851
    Prev
    Next
    INDEX
    Explanations

    say "#"

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

    No Comments

    Negative Logits
    culus
    -14.88
    uild
    -14.81
     startX
    -14.38
    ikipedia
    -14.31
     BUF
    -14.25
     Brewery
    -14.06
     Mines
    -13.88
    rowse
    -13.88
    arring
    -13.81
     batt
    -13.50
    POSITIVE LOGITS
    .Logf
    15.00
    염
    14.56
    ева
    14.38
    FML
    14.13
    //'
    14.06
    мет
    13.88
    SION
    13.75
    转移
    13.69
     sob
    13.63
    权
    13.63
    Activations Density 0.058%

    No Known Activations