© 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. 1513
    Prev
    Next
    INDEX
    Explanations

    say wood

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

    No Comments

    Negative Logits
    抗体
    -27.50
     antibodies
    -27.25
     antibody
    -24.13
     Antib
    -21.25
     Angie
    -20.00
    抗生素
    -20.00
    API
    -19.25
     antibiot
    -18.88
    Ath
    -18.88
     Buddhism
    -18.63
    POSITIVE LOGITS
    木
    21.13
    树木
    18.63
     wood
    18.50
    经济
    18.00
     economics
    17.50
    wood
    17.50
    經濟
    17.25
     trees
    16.50
    木质
    16.25
    Tree
    16.00
    Activations Density 0.034%

    No Known Activations