© 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. 28001
    Prev
    Next
    INDEX
    Explanations

    machine learning algorithms

    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
    ç©¿è¶Ĭå°ı说
    -0.07
    nico
    -0.07
    管çIJĨæľºæŀĦ
    -0.07
    ä¿®çľŁå°ı说
    -0.07
     clearTimeout
    -0.07
     swallowed
    -0.07
    綿
    -0.07
    lagen
    -0.07
     flush
    -0.06
    æĬ½ç©º
    -0.06
    POSITIVE LOGITS
    æľºåĻ¨åŃ¦ä¹ł
    0.11
     algorithms
    0.09
     classifiers
    0.09
    ä¸ŃçļĦæķ°æį®
    0.09
     Algorithms
    0.09
    ervised
    0.09
     datasets
    0.09
    è®Ńç»ĥ
    0.09
     Olah
    0.09
    æķ°æį®æĮĸæİĺ
    0.08
    Activations Density 0.049%

    No Known Activations