© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17471
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals, series, and formulas

    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
    åģĩ
    -0.07
    ardo
    -0.07
    大èĢĮ
    -0.07
    æĥ¯
    -0.07
    ibe
    -0.06
    åıijåĬ¨
    -0.06
    paque
    -0.06
    affle
    -0.06
    åĢĻ
    -0.06
    otten
    -0.06
    POSITIVE LOGITS
     пÑĢиÑģÑĤÑĥ
    0.09
    æĺ¯åĽ½åĨħ
    0.08
    -http
    0.07
    æľ¬å¹³åı°
    0.07
    æľ¬ç¯ĩ
    0.07
    зÑĮ
    0.07
    رÙĬÙĦ
    0.07
    åįłåħ¨åĽ½
    0.07
     Trin
    0.07
    VML
    0.07
    Activations Density 0.004%

    No Known Activations