© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2335
    Prev
    Next
    INDEX
    Explanations

    甲

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

    No Comments

    Negative Logits
     regime
    -15.94
    emple
    -15.94
    示范区
    -15.38
    Ů
    -14.63
    'em
    -14.56
     demos
    -14.31
    Fund
    -13.88
    imento
    -13.81
     parl
    -13.31
    chie
    -13.19
    POSITIVE LOGITS
    甲
    98.00
    乙
    97.00
    丙
    78.50
     meth
    76.00
     Meth
    74.00
    meth
    68.50
    戊
    59.25
    eth
    58.25
     eth
    57.75
     Eth
    57.25
    Activations Density 0.132%

    No Known Activations