© 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. 14427
    Prev
    Next
    INDEX
    Explanations

    assumed

    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
    æĪ·æĪ·
    -0.07
    åıįèĢĮä¼ļ
    -0.07
    第ä¸Ģ人æ°ijåĮ»éĻ¢
    -0.07
    iais
    -0.07
    ughs
    -0.07
    jš
    -0.07
    .arg
    -0.07
    人影
    -0.07
    åıįèĢĮ
    -0.06
    zcze
    -0.06
    POSITIVE LOGITS
    ä¸Ĭæ·»
    0.08
    ä»»åĬ¡æĺ¯
    0.08
    assume
    0.08
    缮æłĩæĺ¯
    0.07
     Assume
    0.07
    åģĩ设
    0.07
     assumed
    0.07
     tasked
    0.07
    è§Ħå®ļ
    0.07
    年以ä¸ĬçļĦ
    0.07
    Activations Density 0.162%

    No Known Activations