© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    [箭] => [在]

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

    No Comments

    Negative Logits
     Rocket
    -22.63
    火箭
    -22.38
     rocket
    -22.25
    rocket
    -21.88
    鹊
    -19.50
     Hawk
    -19.38
    Rocket
    -19.00
    拱
    -18.75
     Ark
    -18.38
     Rockets
    -18.38
    POSITIVE LOGITS
    lambda
    21.38
    λ
    18.88
     λ
    18.75
    Mus
    18.63
     wavelength
    18.50
     lambda
    18.38
    mus
    18.25
    Server
    17.75
    phot
    17.50
    ByteArray
    17.38
    Activations Density 0.256%

    No Known Activations