© 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. 62800
    Prev
    Next
    INDEX
    Explanations

    smoothing capacitor

    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
    æĿĸ
    -0.08
    çĦļ
    -0.08
    ç¾ŀ
    -0.07
    å°ıç¨ĭåºı
    -0.07
    æł·ä¾ĭ
    -0.07
    ôme
    -0.06
    åºĶ纳ç¨İ
    -0.06
    stech
    -0.06
    isty
    -0.06
    èľ¡
    -0.06
    POSITIVE LOGITS
    滤
    0.08
    滤波
    0.08
    elok
    0.08
    .Filter
    0.08
    æį£
    0.08
    _between
    0.08
    波士顿
    0.08
    -refresh
    0.07
     Bott
    0.07
    ahrung
    0.07
    Activations Density 0.006%

    No Known Activations