© 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. 13980
    Prev
    Next
    INDEX
    Explanations

    say spiritual

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

    No Comments

    Negative Logits
    リスク
    -21.63
    市場
    -19.63
    风险
    -19.50
    政府采购
    -18.75
    policy
    -18.63
    風險
    -18.38
    抗菌
    -18.25
    -policy
    -18.13
    政策
    -17.88
     policym
    -17.75
    POSITIVE LOGITS
    spirit
    19.50
     enlightenment
    19.25
     spiritual
    19.25
     spirituality
    18.88
    瞑
    18.75
     spirits
    18.63
    osoph
    18.50
    精神
    18.38
    灵
    18.13
     mystical
    17.88
    Activations Density 0.921%

    No Known Activations