© 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. 19659
    Prev
    Next
    INDEX
    Explanations

    linking words, additions, lists

    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
    æĥ³çŁ¥éģĵçļĦçŃĶæ¡Ī
    -0.08
    ä¾ĽåºĶä¿¡æģ¯
    -0.08
    ypy
    -0.08
    #__
    -0.07
    .SDK
    -0.07
    дÑĮми
    -0.07
    åħ¨æĸĩéĺħ读
    -0.07
    /tty
    -0.07
     noqa
    -0.07
    .exports
    -0.07
    POSITIVE LOGITS
    æ¢ĵ
    0.08
     inoltre
    0.08
     furthermore
    0.07
     additionally
    0.06
    æĸĩå±±
    0.06
    ippe
    0.06
    
    0.06
     pertanto
    0.06
    âĸ
    0.06
    ãĢĤãĢĤ
    0.06
    Activations Density 0.116%

    No Known Activations