© 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. 848
    Prev
    Next
    INDEX
    Explanations

    amyotrophic lateral sclerosis

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

    No Comments

    Negative Logits
    红豆
    -21.00
    绿城
    -20.63
     Somali
    -20.13
     mosque
    -19.88
    绿茶
    -19.75
    伊斯兰
    -19.63
    大唐
    -19.63
    锆
    -19.38
    礁
    -18.50
    海湾
    -18.50
    POSITIVE LOGITS
     Neu
    18.88
     ALS
    18.75
     neurop
    18.63
    病情
    18.50
    ALS
    18.38
    患者
    18.25
     neu
    18.13
    患病
    17.88
    病
    17.75
     neuro
    17.38
    Activations Density 0.114%

    No Known Activations