© 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. 19800
    Prev
    Next
    INDEX
    Explanations

    medical conditions and procedures

    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
     rar
    -0.07
    ª½
    -0.07
    odox
    -0.07
    ekor
    -0.06
     separat
    -0.06
    DataExchange
    -0.06
     ás
    -0.06
     usual
    -0.06
    obile
    -0.06
    usual
    -0.06
    POSITIVE LOGITS
    itim
    0.08
    ãģĵãĤĮãĤĤ
    0.07
    æĬ¼
    0.07
    çĿ£åĬŀ
    0.07
    Ñıд
    0.07
    θή
    0.07
    леб
    0.07
    è¯Ģ
    0.07
    elv
    0.07
    rq
    0.06
    Activations Density 0.003%

    No Known Activations