© 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. 15409
    Prev
    Next
    INDEX
    Explanations

    [token] => [token]

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

    No Comments

    Negative Logits
     Brooke
    -25.63
     Eleanor
    -23.13
     Luk
    -23.13
    .Cl
    -19.88
     Westbrook
    -19.75
    _cl
    -19.75
     Cl
    -19.75
    _Cl
    -19.63
     Jame
    -19.50
     cl
    -19.25
    POSITIVE LOGITS
     Levi
    21.88
    脱发
    20.75
    .rpm
    20.63
     Nissan
    20.38
     Peb
    20.25
    eph
    19.25
     Carson
    19.25
    蛔
    19.13
    车牌
    19.13
     coch
    18.88
    Activations Density 4.257%

    No Known Activations