© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 16140
    Prev
    Next
    INDEX
    Explanations

    say email

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

    No Comments

    Negative Logits
    几何
    -19.38
    -gradient
    -17.50
    Polygon
    -16.88
    (poly
    -16.50
    _polygon
    -16.38
    畅销
    -16.38
    (coeff
    -16.25
    月下
    -16.25
     poly
    -16.25
    酮
    -16.00
    POSITIVE LOGITS
    邮件
    44.75
     email
    43.00
    mail
    43.00
     emails
    42.75
    邮箱
    42.00
     mail
    40.00
     Mail
    40.00
    电子邮件
    39.50
    Mail
    39.50
     Email
    39.00
    Activations Density 0.148%

    No Known Activations