© 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. 15238
    Prev
    Next
    INDEX
    Explanations

    capital D

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

    No Comments

    Negative Logits
     masc
    -20.38
     errorCallback
    -19.88
    豌
    -19.13
    纳斯
    -19.00
     Ivanka
    -18.63
    enal
    -18.13
     Norfolk
    -17.88
    filepath
    -17.88
    胡
    -17.75
     ром
    -17.75
    POSITIVE LOGITS
    utral
    13.13
    Dr
    12.50
    CL
    12.19
    枯
    12.06
    终
    12.06
     Cons
    11.81
    space
    11.81
    Cl
    11.81
    OTE
    11.75
    PS
    11.69
    Activations Density 0.012%

    No Known Activations