© 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. 2272
    Prev
    Next
    INDEX
    Explanations

    ancient Chinese

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

    No Comments

    Negative Logits
    毒品
    -18.63
    棕色
    -18.25
     Cocoa
    -18.25
    动力电池
    -18.13
    cloth
    -17.88
    铝合金
    -17.75
    果汁
    -17.63
     ZIP
    -17.63
    /lab
    -17.38
    苹果
    -17.13
    POSITIVE LOGITS
    piel
    17.38
     CARD
    16.13
    ourn
    15.25
    lice
    15.06
    课文
    14.56
     vn
    14.50
    .minecraft
    14.25
    .card
    14.25
    /card
    14.19
    游戏
    14.13
    Activations Density 0.067%

    No Known Activations