© 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. 28147
    Prev
    Next
    INDEX
    Explanations

    hypostyle architectural C-SPAN Video Library NMR ENDOR

    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
    empla
    -0.08
    بÙĪر
    -0.07
    porte
    -0.07
     diger
    -0.07
     verh
    -0.07
    è´§åĪ°
    -0.07
    หมาย
    -0.07
    ä¸ªå·¥ä½ľ
    -0.07
    ä¼ļ计å¸Ī
    -0.07
    orthy
    -0.07
    POSITIVE LOGITS
    ä¸ĢæĿij
    0.07
    éħįå¥Ĺ
    0.07
    azu
    0.06
    åIJĮæĹ¥
    0.06
    çĻ»
    0.06
    _fact
    0.06
    æĬ½
    0.06
    klam
    0.06
    ubs
    0.06
    à¤ľà¤¨
    0.06
    Activations Density 0.001%

    No Known Activations