© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49793
    Prev
    Next
    INDEX
    Explanations

    numerical calculations and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩijæĸ¯
    -0.07
     gjerne
    -0.07
    大åĬ¿
    -0.07
    iami
    -0.07
    idos
    -0.06
    rolling
    -0.06
    åŁ¹åħ»åŃ©åŃIJ
    -0.06
     Rockefeller
    -0.06
    åIJĦä¸ĵä¸ļ
    -0.06
     "@
    -0.06
    POSITIVE LOGITS
    ICAS
    0.07
    Places
    0.07
    oby
    0.07
    éĩİ
    0.07
    cardo
    0.07
     Pala
    0.07
     Franken
    0.07
     IK
    0.07
    æĢİ麽
    0.07
     wzgl
    0.07
    Activations Density 0.056%

    No Known Activations