© 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. 23387
    Prev
    Next
    INDEX
    Explanations

    alloc, date, or sequential numbers

    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
    Õ¡Õ¶
    -0.07
    ãĥģãĥ£ãĥ³
    -0.07
    oret
    -0.07
     météo
    -0.06
    bec
    -0.06
    ç»´çĶŁç´łåĴĮ
    -0.06
    pañol
    -0.06
    parg
    -0.06
    ments
    -0.06
    clair
    -0.06
    POSITIVE LOGITS
     \"
    0.08
    vre
    0.07
    æķħæѤ
    0.07
     rectific
    0.07
    خد
    0.07
    anceled
    0.06
     asum
    0.06
     Seul
    0.06
    æĴ°ç¨¿
    0.06
     asal
    0.06
    Activations Density 0.003%

    No Known Activations