© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15693
    Prev
    Next
    INDEX
    Explanations

    [depends] => [depends]

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

    No Comments

    Negative Logits
    滚
    -17.50
    xff
    -15.81
    VRT
    -15.75
    谯
    -15.75
    美
    -15.56
    ermann
    -15.19
    (tol
    -14.88
    asco
    -14.63
    WSC
    -14.56
     PCS
    -14.50
    POSITIVE LOGITS
    คาร
    19.63
     crane
    19.00
    .son
    18.50
     son
    17.88
     SON
    17.63
     Leone
    17.50
     Crane
    17.38
     plut
    17.25
    SON
    17.25
    oni
    17.13
    Activations Density 0.221%

    No Known Activations