© 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. 14702
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences and symbols

    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
    YTE
    -0.07
    ÚĨÙĩ
    -0.06
    å°±æĺ¯æĬĬ
    -0.06
    ön
    -0.06
    onnier
    -0.06
    á
    -0.06
    ute
    -0.06
     falling
    -0.06
    oris
    -0.06
     falls
    -0.06
    POSITIVE LOGITS
    gota
    0.08
    eby
    0.08
    âĸ·
    0.08
    ẻo
    0.07
    åĽ¾ç½ij
    0.07
    schluss
    0.07
    tahan
    0.07
    leman
    0.07
    å°Ķ夫
    0.07
    umas
    0.07
    Activations Density 0.001%

    No Known Activations