© 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. 2837
    Prev
    Next
    INDEX
    Explanations

    say "permit"

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

    No Comments

    Negative Logits
    曲线
    -16.25
     curves
    -15.63
     meds
    -14.81
     curve
    -14.75
    注
    -14.50
     tube
    -14.50
    德
    -14.25
    ạp
    -14.06
    ter
    -14.06
     Curve
    -13.94
    POSITIVE LOGITS
    perm
    59.75
     perm
    56.75
     permit
    53.75
     Per
    52.50
    _perm
    52.25
    Per
    52.00
    Perm
    51.50
     Permit
    50.75
    permit
    50.25
    .perm
    49.75
    Activations Density 0.115%

    No Known Activations