© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1542
    Prev
    Next
    INDEX
    Explanations

    [pH] => [pH]

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

    No Comments

    Negative Logits
     pH
    -36.50
    PH
    -28.75
     PH
    -27.50
    _PH
    -26.75
    APH
    -22.50
     ph
    -22.38
    phi
    -21.75
    PHA
    -21.50
    _ph
    -21.38
    ph
    -21.00
    POSITIVE LOGITS
     legal
    16.13
     security
    15.56
     Security
    15.00
    苗
    13.81
    法律
    13.69
    影片
    13.63
     SECURITY
    13.63
    -mail
    13.50
    forest
    13.50
    ísticas
    13.31
    Activations Density 0.087%

    No Known Activations