© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14404
    Prev
    Next
    INDEX
    Explanations

    surname Zhang

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

    No Comments

    Negative Logits
    Mahon
    -19.25
    ATCH
    -19.25
    coh
    -18.63
    ej
    -18.50
    OMP
    -18.00
    vh
    -17.88
    vfs
    -17.50
     Wilmington
    -17.50
    eph
    -17.38
     ench
    -17.00
    POSITIVE LOGITS
    Brad
    18.75
    bra
    18.00
     Brussels
    17.88
    翠
    17.63
    ster
    17.50
     Brad
    17.25
     kr
    17.25
     creed
    17.13
     steroids
    17.00
    Kr
    16.75
    Activations Density 1.374%

    No Known Activations