© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15051
    Prev
    Next
    INDEX
    Explanations

    aircraft names

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

    No Comments

    Negative Logits
    aro
    -16.50
    eln
    -15.94
    apan
    -15.38
    ள
    -14.69
    .maps
    -14.38
    etur
    -14.31
    acula
    -14.31
    tract
    -14.13
    eland
    -14.00
    avery
    -14.00
    POSITIVE LOGITS
     findOne
    14.38
    ensis
    13.38
    垢
    13.25
    澤
    13.19
    一对
    13.06
    igner
    13.06
    렁
    13.06
     sola
    12.94
    剁
    12.69
    ńs
    12.63
    Activations Density 0.064%

    No Known Activations