© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1416
    Prev
    Next
    INDEX
    Explanations

    say card

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

    No Comments

    Negative Logits
    几何
    -59.75
     geometric
    -59.25
     geometry
    -51.75
     geomet
    -48.50
     Geometry
    -47.75
     Ge
    -47.00
    _geometry
    -45.25
     geom
    -44.25
    Geometry
    -43.50
    _GE
    -43.00
    POSITIVE LOGITS
    カード
    19.75
    /player
    17.13
     DSP
    16.38
     McCarthy
    15.94
     TSRMLS
    15.81
    卡片
    15.63
    CARD
    15.63
     player
    15.56
    (players
    15.50
    <Player
    15.38
    Activations Density 0.093%

    No Known Activations