© 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. 65527
    Prev
    Next
    INDEX
    Explanations

    clinical analysis and outcomes

    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
    uhe
    -0.07
    çIJ³å¨ľ
    -0.07
    对åIJĦç§į
    -0.07
     aficion
    -0.07
    emie
    -0.07
    ungan
    -0.07
    Snippet
    -0.07
    oria
    -0.07
    缴æİ¥æĪĸéĹ´æİ¥
    -0.07
     Pisc
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºè¿ĻäºĽ
    0.07
    ides
    0.07
    akit
    0.06
    è¬
    0.06
    æł½
    0.06
    ebles
    0.06
    hm
    0.06
    μαÏĦο
    0.06
    arse
    0.06
    æľºåħ³
    0.06
    Activations Density 0.030%

    No Known Activations