© 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. 15468
    Prev
    Next
    INDEX
    Explanations

    [ok] => [bok]

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

    No Comments

    Negative Logits
    =q
    -25.75
     qu
    -25.75
     Qu
    -24.88
    (qu
    -24.63
    QUE
    -24.50
    qu
    -23.88
    QU
    -23.88
     QA
    -23.75
    ques
    -23.63
    qua
    -23.50
    POSITIVE LOGITS
     anonymity
    17.00
    茂名
    16.75
     Dakota
    16.50
    SharedPreferences
    16.25
     Sloven
    16.13
    .getLongitude
    15.69
    连云港
    15.56
    晔
    15.56
    RecyclerView
    15.50
    _visibility
    15.44
    Activations Density 0.739%

    No Known Activations