© 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. 15006
    Prev
    Next
    INDEX
    Explanations

    say "tree names"

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

    No Comments

    Negative Logits
    槿
    -18.25
    urma
    -17.88
    urm
    -17.88
    素质
    -17.50
    nim
    -17.25
    cats
    -17.25
    suming
    -17.25
    cams
    -17.25
    uffles
    -16.63
    vfs
    -16.50
    POSITIVE LOGITS
     Dillon
    13.75
    lor
    13.19
    .CONTENT
    12.94
    edis
    12.56
    eph
    12.25
     MULTI
    12.19
    ci
    11.88
    的喜爱
    11.69
     ".";↵
    11.69
    亵
    11.63
    Activations Density 0.075%

    No Known Activations