© 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. 21600
    Prev
    Next
    INDEX
    Explanations

    protected status

    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
    iller
    -0.07
    cé
    -0.07
    bew
    -0.06
    rg
    -0.06
    ÑģÑĤе
    -0.06
    åĽŀæĿ¥çļĦ
    -0.06
    cdf
    -0.06
    æĪIJé¾Ļ
    -0.06
    пам
    -0.06
    称å¾Ĺä¸Ĭ
    -0.06
    POSITIVE LOGITS
    veja
    0.08
     appunto
    0.07
     bè
    0.07
    ikian
    0.07
    æĸ¯åį¡
    0.06
    åįĹå¸Ĥ
    0.06
    кина
    0.06
    verfahren
    0.06
     Cooperativa
    0.06
    Warehouse
    0.06
    Activations Density 0.202%

    No Known Activations