© 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. 2780
    Prev
    Next
    INDEX
    Explanations

    say sec

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

    No Comments

    Negative Logits
    帝国
    -16.63
     regress
    -16.63
    Marg
    -16.00
     Marg
    -15.81
     methyl
    -15.75
    表演
    -15.56
     tat
    -15.38
    _ant
    -14.94
     hóa
    -14.88
     retro
    -14.75
    POSITIVE LOGITS
     Sec
    57.75
     sec
    56.25
    (sec
    55.00
    Sec
    54.25
    sec
    53.50
    .sec
    49.75
     securing
    49.75
    _sec
    49.25
     SEC
    49.25
     secured
    49.00
    Activations Density 0.069%

    No Known Activations