© 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. 14687
    Prev
    Next
    INDEX
    Explanations

    say 9

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

    No Comments

    Negative Logits
    橛
    -18.38
    woke
    -18.00
     QMap
    -17.63
    兰花
    -17.63
    _qos
    -17.63
    уж
    -17.50
     ceilings
    -17.38
    oose
    -17.38
    bud
    -17.13
    уль
    -17.13
    POSITIVE LOGITS
     st
    21.38
    St
    20.63
    st
    19.88
     St
    19.75
    ST
    19.25
    pha
    17.75
    STAR
    17.63
    /St
    17.63
    STA
    17.00
    -St
    16.75
    Activations Density 0.034%

    No Known Activations