© 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. 2140
    Prev
    Next
    INDEX
    Explanations

    say prescription

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

    No Comments

    Negative Logits
    fund
    -16.25
    (mut
    -15.38
    IONS
    -15.38
    Fund
    -15.00
     fund
    -14.88
    巨
    -14.75
    wagon
    -14.69
    mel
    -14.63
    .Cap
    -14.63
    Entropy
    -14.38
    POSITIVE LOGITS
    Pres
    73.50
    pres
    69.50
     Pres
    68.50
     pres
    68.00
    _pres
    61.00
     prescription
    59.50
    -pres
    58.25
     PRES
    56.00
     prescriptions
    54.00
     Prescription
    54.00
    Activations Density 0.091%

    No Known Activations