© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14421
    Prev
    Next
    INDEX
    Explanations

    say 2

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

    No Comments

    Negative Logits
    芝
    -17.88
     Chic
    -16.63
    erialized
    -16.50
     ridge
    -16.38
     Roose
    -16.13
    adem
    -16.00
     Zig
    -15.88
    ÖZ
    -15.63
    ₂
    -15.56
     charger
    -15.25
    POSITIVE LOGITS
    ста
    20.00
    스타
    19.38
    eut
    18.75
    usta
    17.75
    quat
    17.75
    сты
    17.75
    スタ
    17.38
    lng
    17.00
    sto
    16.50
    antasy
    16.13
    Activations Density 0.027%

    No Known Activations