© 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. 62756
    Prev
    Next
    INDEX
    Explanations

    math function or equation notation

    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
    aced
    -0.07
    aldas
    -0.07
    cest
    -0.07
    ¾
    -0.07
    felder
    -0.07
    å½¹
    -0.07
    åŁ¹æł¹
    -0.06
    idente
    -0.06
    åĩłç»ı
    -0.06
    дли
    -0.06
    POSITIVE LOGITS
    dsm
    0.07
    tide
    0.07
    æĥ³æĸ¹
    0.07
    à¹īà¸Ńà¸Ļ
    0.06
    _JS
    0.06
    åıĤåĬłäºĨä¼ļè®®
    0.06
    åķĨè¡Į
    0.06
    ngine
    0.06
    -preview
    0.06
    éľ²
    0.06
    Activations Density 0.011%

    No Known Activations