© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 671
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    渠
    -16.88
    .EVT
    -15.63
    三峡
    -15.00
     PANEL
    -14.75
    法
    -14.56
    筏
    -14.44
    ái
    -14.44
     estad
    -14.44
    rie
    -14.38
    .setType
    -14.31
    POSITIVE LOGITS
     Ghana
    18.38
     iOS
    16.25
     Ethiopian
    15.88
     Ethiopia
    15.81
    苏联
    15.75
     Russia
    15.50
    hana
    15.31
     Ukrainian
    15.25
     South
    15.25
    iOS
    15.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.