© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with theta or frac

    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
    ä¸įåı¯æĢĿè®®
    -0.09
    åĭĩå¾Ģ缴åīį
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    两åѦä¸Ģåģļ
    -0.08
    身临åħ¶å¢ĥ
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    åħ¢åħ¢ä¸ļä¸ļ
    -0.07
    ats
    -0.07
    åĬłæĭ¿å¤§
    -0.07
    ÑĥÑĢ
    -0.07
    POSITIVE LOGITS
    åIJĪåIJĮæŶ
    0.08
    åij¨å²ģçļĦ
    0.07
    icular
    0.07
    尼迪
    0.07
    ì²Ń
    0.07
    ecast
    0.07
    ographique
    0.07
     hãi
    0.07
    fulness
    0.07
    ī´
    0.06
    Activations Density 0.015%

    No Known Activations