© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1286
    Prev
    Next
    INDEX
    Explanations

    architectural dimensions

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

    No Comments

    Negative Logits
    献血
    -18.25
    自来水
    -17.75
     Cycling
    -17.63
    口水
    -17.13
     Tide
    -17.13
    цикл
    -16.88
    招聘
    -16.88
     hydration
    -16.63
     thirsty
    -16.50
     Manning
    -16.38
    POSITIVE LOGITS
    民国
    13.88
    .googleapis
    13.88
    琉璃
    13.00
    券
    12.94
     bruk
    12.75
    ulus
    12.19
    ходим
    12.00
    ic
    12.00
    院
    12.00
    olith
    11.75
    Activations Density 0.112%

    No Known Activations