© 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. 14961
    Prev
    Next
    INDEX
    Explanations

    say "capitalized name parts"

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

    No Comments

    Negative Logits
    YA
    -23.13
    VI
    -18.88
    UST
    -18.13
    CPP
    -17.63
    UE
    -17.13
    UI
    -16.88
    ACION
    -16.63
    AXB
    -16.63
    UDA
    -16.63
    acion
    -16.63
    POSITIVE LOGITS
    罢
    14.25
     arc
    13.94
    �
    13.56
    (arc
    13.56
    ertz
    13.31
    chts
    13.31
    rends
    13.31
    inherit
    13.25
     james
    12.94
     Bar
    12.88
    Activations Density 0.073%

    No Known Activations