© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 349
    Prev
    Next
    INDEX
    Explanations

    say "?H"

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

    No Comments

    Negative Logits
     Orlando
    -18.75
    (pt
    -15.56
    巩
    -15.06
     rept
    -14.94
     Москов
    -14.00
     Madrid
    -13.69
     Petr
    -13.44
    ict
    -13.44
    兽
    -13.44
    riculum
    -13.31
    POSITIVE LOGITS
     DH
    57.00
     KH
    56.75
     MH
    56.25
    GH
    53.75
     BH
    53.50
     AH
    53.00
    DH
    53.00
     GH
    52.50
    MH
    52.50
     RH
    52.00
    Activations Density 0.519%

    No Known Activations