© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1997
    Prev
    Next
    INDEX
    Explanations

    [card] => [card]

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

    No Comments

    Negative Logits
     card
    -59.75
    Card
    -57.25
    卡
    -57.00
    card
    -56.25
     Card
    -55.75
     cards
    -55.50
    -card
    -53.25
    _card
    -53.00
     CARD
    -52.50
    CARD
    -52.50
    POSITIVE LOGITS
    几何
    17.75
     Js
    17.63
    js
    16.13
    dyn
    16.00
     js
    15.69
    _GE
    15.50
     geometry
    14.81
     Geometry
    14.63
    /js
    14.19
     Economic
    14.06
    Activations Density 0.085%

    No Known Activations