© 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. 14047
    Prev
    Next
    INDEX
    Explanations

    say mail

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

    No Comments

    Negative Logits
    calc
    -17.13
    _calc
    -17.00
    .eval
    -16.25
    评价
    -16.25
    结构调整
    -16.13
    Eval
    -15.63
     Eval
    -15.44
     calcul
    -15.19
     eval
    -15.13
    .calc
    -15.06
    POSITIVE LOGITS
    邮件
    40.25
     mails
    38.00
    发送
    38.00
    郵
    36.75
     mail
    36.00
    mail
    35.25
    信箱
    35.25
     emails
    35.00
    -mail
    34.75
     Mail
    34.75
    Activations Density 0.788%

    No Known Activations