© 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. 2270
    Prev
    Next
    INDEX
    Explanations

    say "Wil" names

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

    No Comments

    Negative Logits
     poly
    -18.88
    Poly
    -18.25
    ethical
    -17.13
    集成
    -17.13
     Poly
    -17.00
    poly
    -16.88
     Modi
    -16.50
    _poly
    -16.25
    聚
    -16.00
     Maxim
    -15.69
    POSITIVE LOGITS
     Wil
    65.50
    Wil
    63.50
     wil
    43.50
    wil
    38.75
    威尔
    33.50
    万
    27.50
    萬
    21.50
     Wilhelm
    21.38
     Wilkinson
    20.75
     Wik
    19.50
    Activations Density 0.064%

    No Known Activations