© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15727
    Prev
    Next
    INDEX
    Explanations

    say spectrum

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

    No Comments

    Negative Logits
    udent
    -16.75
    退税
    -16.50
     Debt
    -15.81
    债务
    -15.38
    onald
    -15.19
     QUI
    -15.13
     cashier
    -14.94
    -handler
    -14.63
     debt
    -14.44
     repayment
    -14.44
    POSITIVE LOGITS
    范围
    44.00
     range
    39.75
     scope
    38.00
    范围内
    37.00
    範
    36.25
     Scope
    35.25
    range
    35.00
    scope
    35.00
     ranges
    34.50
    _range
    34.25
    Activations Density 0.428%

    No Known Activations