© 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. 32941
    Prev
    Next
    INDEX
    Explanations

    mathematical operators 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
    extract
    -0.06
    è¿ĩ客
    -0.06
    ç¥ĸåĽ½
    -0.06
    procs
    -0.06
    票æķ°
    -0.06
    osa
    -0.06
    .CreateDirectory
    -0.06
    ধান
    -0.06
    转è¿ĩ头
    -0.06
    ftime
    -0.06
    POSITIVE LOGITS
    @(
    0.08
    ahan
    0.08
     wed
    0.08
    rist
    0.07
    åķĨçļĦ
    0.07
    åķĨ
    0.07
    chan
    0.07
    è·Łäºº
    0.07
    ières
    0.07
    为ä»Ģä¹Īä¼ļ
    0.07
    Activations Density 0.021%

    No Known Activations