© 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. 1823
    Prev
    Next
    INDEX
    Explanations

    social insurance

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

    No Comments

    Negative Logits
    佛法
    -18.88
    arth
    -18.63
     VPN
    -18.13
    泳
    -18.00
    >Email
    -18.00
    VPN
    -18.00
    佛
    -17.88
     Lambert
    -17.63
    禅
    -17.50
     jerseys
    -17.38
    POSITIVE LOGITS
    ATOM
    17.88
    edly
    16.38
    cling
    15.56
     Washington
    15.25
    一脚
    15.00
    华盛顿
    14.56
    国防部
    14.31
     Metropolitan
    14.19
     Mac
    14.06
    cloud
    14.06
    Activations Density 0.061%

    No Known Activations