© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14135
    Prev
    Next
    INDEX
    Explanations

    say member

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

    No Comments

    Negative Logits
    验
    -19.63
    ��
    -17.25
    latin
    -15.94
     classname
    -15.25
     Delhi
    -15.19
    检验
    -14.88
    驗
    -14.88
    Delimiter
    -14.31
    认证
    -14.31
    戴着
    -14.25
    POSITIVE LOGITS
    member
    22.63
     Member
    21.50
    MEM
    20.88
     member
    20.50
    -member
    20.25
    成员
    19.88
     Members
    19.50
     members
    19.00
    members
    18.75
    (member
    18.50
    Activations Density 0.249%

    No Known Activations