© 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. 1730
    Prev
    Next
    INDEX
    Explanations

    [network] => [related]

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

    No Comments

    Negative Logits
    网络
    -57.75
     network
    -53.00
     networks
    -51.75
    Network
    -51.25
     Network
    -51.00
     Networks
    -49.75
    network
    -48.75
     NETWORK
    -48.75
    -network
    -48.50
     Networking
    -48.00
    POSITIVE LOGITS
     electrodes
    13.81
     Ele
    13.81
     SQLAlchemy
    13.63
    宰
    13.63
    Ele
    13.44
    rst
    13.38
     élect
    13.31
    .tokens
    12.88
     edm
    12.75
    ドル
    12.75
    Activations Density 0.199%

    No Known Activations