© 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. 43210
    Prev
    Next
    INDEX
    Explanations

    chemical compounds, technology, and locations

    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
    adak
    -0.08
    udas
    -0.07
    systems
    -0.07
    æĮĩå®ļåľ°çĤ¹
    -0.07
    annot
    -0.07
    ouv
    -0.07
    åĨ³å®ļæĢ§
    -0.07
    areas
    -0.07
    æĤ¨çİ°åľ¨çļĦä½įç½®
    -0.07
    ä¸įåı¯ç¼ºå°ij
    -0.06
    POSITIVE LOGITS
    çļĦç¼ĺæķħ
    0.07
    åħ¨æĸĩéĺħ读
    0.07
    åĽ¢åľĨ
    0.06
    cian
    0.06
     waarvan
    0.06
    æľ¬èº«å°±æĺ¯
    0.06
    artal
    0.06
    åŀĭæħĭ
    0.06
     pronounced
    0.06
    steen
    0.06
    Activations Density 0.064%

    No Known Activations