© 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. 60491
    Prev
    Next
    INDEX
    Explanations

    years, times, patients, countries

    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
    æĢİä¹Īæł·äºĨ
    -0.07
    æľĪçĶŁ
    -0.07
    flen
    -0.07
    å±Ģéķ¿
    -0.07
     appunto
    -0.06
    cial
    -0.06
    EMY
    -0.06
    _ml
    -0.06
    thead
    -0.06
    DDS
    -0.06
    POSITIVE LOGITS
    æľ¬åħ¬ä¼Ĺåı·
    0.08
    mater
    0.08
    .Compile
    0.08
    ÐŀÐĴÐŀ
    0.08
    ç²Ĺçķ¥
    0.07
    èİ·å¾Ĺè¶ħè¿ĩ
    0.07
    ipers
    0.07
     kelu
    0.07
    _ASSUME
    0.07
     Mattis
    0.07
    Activations Density 0.003%

    No Known Activations