© 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. 41155
    Prev
    Next
    INDEX
    Explanations

    Arrow, color, AF, Int, Heading

    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
    çıĬ
    -0.08
    ä¸ĭåŃ¦æľŁ
    -0.07
    å®ŀä¹łæľŁéĹ´
    -0.07
    .qq
    -0.07
    URLConnection
    -0.07
    umed
    -0.07
    ÑijÑĤ
    -0.06
    æ»ļ
    -0.06
    .Addr
    -0.06
    滾
    -0.06
    POSITIVE LOGITS
    ä½ıæĪ¿åŁİ乡建设
    0.07
    ä¸įæĭĶ
    0.07
    KeyId
    0.07
    çļĦæŃ»
    0.07
    ä¸įä¸ĭ
    0.07
    زÙĩ
    0.06
    é«ĺåİŁ
    0.06
    åĬłæĭ¿å¤§
    0.06
    uyan
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.06
    Activations Density 0.022%

    No Known Activations