© 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. 1644
    Prev
    Next
    INDEX
    Explanations

    code delimiters and identifiers

    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
    ä¾Ŀç¨Ģ
    -0.06
     José
    -0.06
    olé
    -0.06
    缴éĿ¢
    -0.06
    est
    -0.06
    ehl
    -0.06
    ä¸īé«ĺ
    -0.06
    ׳×ĵ
    -0.06
    æĬĸ
    -0.06
    éķ¿åģĩ
    -0.06
    POSITIVE LOGITS
    iros
    0.07
    AsString
    0.07
    aden
    0.07
    mate
    0.07
    åĪ¶éĢłæľīéĻIJåħ¬åı¸
    0.07
    æĺ
    0.07
    èĢĮæĺĵ
    0.07
    _launcher
    0.07
    -rating
    0.07
     ÑģообÑī
    0.07
    Activations Density 0.008%

    No Known Activations