© 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. 61437
    Prev
    Next
    INDEX
    Explanations

    second or subsequent ordinals

    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
    uccio
    -0.08
     listen
    -0.07
    _PRIMARY
    -0.07
    JM
    -0.07
    ukur
    -0.07
     supposedly
    -0.07
    è¯ĨåĪ«äºĮç»´çłģ
    -0.06
    .cgi
    -0.06
    orne
    -0.06
    cio
    -0.06
    POSITIVE LOGITS
    æīį对
    0.09
    æĽ´ç¬¦åIJĪ
    0.09
    æīįæĺ¯çľŁæŃ£çļĦ
    0.09
    æīįæĺ¯
    0.09
    ãģ»ãģĨãģĮ
    0.08
    è¿Ļæīįæĺ¯
    0.08
    ãģ®æĸ¹ãģĮ
    0.08
    лин
    0.07
    -not
    0.07
     inilah
    0.07
    Activations Density 0.001%

    No Known Activations