© 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. 14559
    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
    jis
    -18.38
    -dismiss
    -18.25
    席
    -17.63
    iswa
    -17.25
    议事
    -16.88
    Scrollbar
    -16.63
    ikki
    -16.63
    西红柿
    -16.38
     JQuery
    -16.38
     heir
    -16.38
    POSITIVE LOGITS
     Megan
    15.81
     Frost
    15.81
     Petra
    15.38
    斯特
    15.31
    _ln
    15.25
    揆
    15.25
     Ing
    15.13
    Ing
    15.13
     frost
    15.00
    _stub
    14.88
    Activations Density 0.027%

    No Known Activations