© 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. 4274
    Prev
    Next
    INDEX
    Explanations

    relativistic, constituent, insulators, Vick, Salvatore

    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
     Seger
    -0.08
    inja
    -0.07
    issen
    -0.07
    çİ°å½¹
    -0.07
    agini
    -0.07
    emma
    -0.07
    .gg
    -0.07
    æĹłèıĮ
    -0.07
    èŀŁ
    -0.07
    ä¸ĩåıª
    -0.07
    POSITIVE LOGITS
    rasz
    0.08
    «
    0.07
    eller
    0.07
    豺
    0.07
     veloc
    0.07
    éĢŁ
    0.07
    çĮİ
    0.07
    é¢Ħè¨Ģ
    0.07
     Decompiled
    0.07
    ouser
    0.07
    Activations Density 0.013%

    No Known Activations