© 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. 15500
    Prev
    Next
    INDEX
    Explanations

    peaks

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

    No Comments

    Negative Logits
    phere
    -19.13
    _sector
    -17.00
    ottie
    -16.88
    /save
    -16.63
    _budget
    -16.25
    ialis
    -15.75
    _cycle
    -15.63
     fencing
    -15.56
    ouncil
    -15.31
    _pipeline
    -15.31
    POSITIVE LOGITS
     peak
    27.50
    峰
    26.50
     Peak
    24.75
    peak
    23.88
     peaks
    22.63
    峰值
    21.88
    Peak
    21.50
     Peaks
    20.63
    ピー
    20.38
     peaked
    20.25
    Activations Density 0.084%

    No Known Activations