© 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. 1643
    Prev
    Next
    INDEX
    Explanations

    cytokine names

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

    No Comments

    Negative Logits
    幡
    -21.13
    ELY
    -19.63
    pixel
    -19.13
    IVED
    -18.75
     scrollbar
    -18.50
    ellas
    -18.38
    万象
    -18.00
     muslim
    -17.88
     flaming
    -17.88
    elige
    -17.75
    POSITIVE LOGITS
    愧
    12.38
    ա
    12.06
    こそ
    11.94
     RO
    11.56
    矿
    11.38
     Mountain
    11.19
    网
    11.06
    昆山
    11.00
    վ
    10.94
    安全
    10.88
    Activations Density 0.066%

    No Known Activations