© 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. 49198
    Prev
    Next
    INDEX
    Explanations

    months and 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
    enberg
    -0.08
    ÑĦа
    -0.08
    ilhar
    -0.07
    zzi
    -0.07
    acom
    -0.07
    entro
    -0.07
    æĪij家
    -0.06
    以ä¸ĬçļĦ
    -0.06
    -com
    -0.06
    ilha
    -0.06
    POSITIVE LOGITS
    éĽªæ¢¨
    0.07
    ؤÙĦ
    0.07
    è°ļ
    0.07
    æģ°
    0.07
    _tw
    0.07
    tal
    0.07
    assin
    0.07
    æľĢæĸ°æĸĩç«ł
    0.07
     Jas
    0.07
    аÑĤелÑĮ
    0.07
    Activations Density 0.018%

    No Known Activations