© 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. 13430
    Prev
    Next
    INDEX
    Explanations

    programming keywords after č

    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
     later
    -0.07
    ç°§
    -0.07
     serialVersionUID
    -0.07
    later
    -0.07
     feel
    -0.06
    ainer
    -0.06
    æĹ¥åIJİ
    -0.06
     Ira
    -0.06
    anga
    -0.06
    udet
    -0.06
    POSITIVE LOGITS
     lest
    0.08
    åĥ
    0.08
    iš
    0.07
    磨éļ¾
    0.07
    oce
    0.07
    西èĴĻ
    0.07
    ิà¸ĩ
    0.07
     phần
    0.07
    èĪŀ
    0.07
    _EXISTS
    0.07
    Activations Density 0.001%

    No Known Activations