© 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. 15767
    Prev
    Next
    INDEX
    Explanations

    say power

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

    No Comments

    Negative Logits
     aromatic
    -17.13
    芳香
    -16.88
    麝
    -16.38
    箅
    -15.13
    鞣
    -14.88
     Venez
    -14.56
     arom
    -14.50
    ğ
    -14.19
    Ứ
    -14.06
    segue
    -13.94
    POSITIVE LOGITS
     power
    75.00
    power
    69.00
     Power
    67.50
    Power
    66.50
    _power
    64.50
    (power
    64.00
     POWER
    64.00
    -power
    62.25
    POWER
    61.75
    .power
    60.75
    Activations Density 0.220%

    No Known Activations