© 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. 14887
    Prev
    Next
    INDEX
    Explanations

    say hex digits

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

    No Comments

    Negative Logits
    YE
    -17.50
    Ｄ
    -17.38
    /us
    -16.38
    antar
    -16.38
    ço
    -16.38
    ehler
    -16.13
    bie
    -16.00
    oS
    -16.00
    andard
    -16.00
    BS
    -16.00
    POSITIVE LOGITS
    粽子
    19.75
     Hemp
    18.88
    金沙
    18.38
    綦
    18.13
     Klopp
    17.88
     Twitch
    17.75
    烙
    16.88
    金山
    16.88
     hemp
    16.75
     Liverpool
    16.63
    Activations Density 0.016%

    No Known Activations