© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1317
    Prev
    Next
    INDEX
    Explanations

    storage size

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

    No Comments

    Negative Logits
    コード
    -20.13
     code
    -20.00
     codes
    -19.88
     Pharmaceutical
    -19.13
    code
    -18.88
    代码
    -18.88
    Code
    -18.50
     coding
    -18.13
    _codes
    -17.88
    Urban
    -17.88
    POSITIVE LOGITS
     en
    19.63
    ,en
    15.75
    /card
    15.63
    .cv
    15.38
    沸
    15.31
    bij
    14.94
     Ridge
    14.88
     po
    14.63
    烧
    14.44
    (card
    14.38
    Activations Density 0.016%

    No Known Activations