© 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. 1780
    Prev
    Next
    INDEX
    Explanations

    [mouse] => [mouse]

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

    No Comments

    Negative Logits
    CSS
    -20.75
    _CSS
    -19.63
     CSS
    -18.75
     Mouse
    -17.63
     mouse
    -17.25
    バス
    -17.25
    [token
    -16.75
    _css
    -16.63
    -css
    -16.38
     tourist
    -16.25
    POSITIVE LOGITS
     Alphabet
    20.63
     matrix
    20.38
    矩阵
    19.38
     Ridley
    18.75
    matrix
    18.50
    alphabet
    18.38
     MATRIX
    18.13
     Geh
    17.88
    -alpha
    17.75
    切尔
    17.75
    Activations Density 0.443%

    No Known Activations