© 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. 46872
    Prev
    Next
    INDEX
    Explanations

    adverse medical 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
    æĴĩ
    -0.08
    为è°ģ
    -0.08
    çĦ¶å¤§
    -0.08
    天æīį
    -0.08
     ÐłÐ°Ð·ÑĢе
    -0.07
     intuit
    -0.07
    orelease
    -0.07
    足ãĤĬãģªãģĦ
    -0.07
     Mati
    -0.07
    à¸į
    -0.07
    POSITIVE LOGITS
     complications
    0.11
    åıijå±ķ为
    0.11
    éķ¿æľŁçļĦ
    0.10
    åıijå±ķæĪIJ
    0.10
    éķ¿æľŁ
    0.10
    并åıijçĹĩ
    0.10
    åį±å®³
    0.09
    åį±åıĬ
    0.09
     lifelong
    0.09
     komplik
    0.09
    Activations Density 0.314%

    No Known Activations