© 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. 22630
    Prev
    Next
    INDEX
    Explanations

    nullable, optional chaining, immutable, version

    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
    auan
    -0.07
     ngần
    -0.06
    رز
    -0.06
    ç®Ĺä¸įä¸Ĭ
    -0.06
    _outline
    -0.06
     besides
    -0.06
    ä¹Łè®¸ä¼ļ
    -0.06
    vat
    -0.06
    à·Ļ
    -0.06
    ductive
    -0.06
    POSITIVE LOGITS
    çī¹æĦı
    0.08
     Mois
    0.08
    -aware
    0.08
    tre
    0.08
    æĦıåij³
    0.07
    æķħæĦı
    0.07
    æķħèĢĮ
    0.07
    åĪ»æĦı
    0.07
    alai
    0.07
    ubb
    0.07
    Activations Density 0.021%

    No Known Activations