© 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. 48857
    Prev
    Next
    INDEX
    Explanations

    statin, herpesvirus, viral, insecticide, vitamin

    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
     напÑĢимеÑĢ
    -0.08
    ä¾ĭå¦Ĥ
    -0.08
     például
    -0.08
    ä¼¼ä¹İæĺ¯
    -0.07
    缴æİ¥æĪĸ
    -0.07
    ewise
    -0.07
    æľįåĬ¡æĦıè¯Ĩ
    -0.07
     misalnya
    -0.07
     ÐĿапÑĢимеÑĢ
    -0.07
     beispielsweise
    -0.07
    POSITIVE LOGITS
    ç±»
    0.09
    ãģ®ä¸Ńãģ§ãĤĤ
    0.09
    çļĦä¸Ģç±»
    0.09
    ãģ®ä¸Ńãģ§ãģ¯
    0.08
    çļĦä¸Ģåijĺ
    0.08
    èĢĮä¸Ķæĺ¯
    0.08
    alkan
    0.08
    çļĦä¸Ģç§į
    0.07
     subclass
    0.07
    ç±»çļĦ
    0.07
    Activations Density 0.440%

    No Known Activations