© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15369
    Prev
    Next
    INDEX
    Explanations

    eggplant

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

    No Comments

    Negative Logits
    (wx
    -23.75
     Apollo
    -23.00
    醴
    -22.63
    磷
    -22.13
    	wx
    -22.00
     phosph
    -21.88
    佛山
    -21.13
     Lunar
    -20.88
     lunar
    -20.75
     Gaines
    -20.63
    POSITIVE LOGITS
    茄子
    22.50
     assassin
    20.88
    抢劫
    20.75
    茄
    20.50
     Assassin
    19.25
    鱿
    19.25
    椒
    18.88
    垃
    18.63
    佣
    18.25
     Levi
    18.13
    Activations Density 5.944%

    No Known Activations