© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39542
    Prev
    Next
    INDEX
    Explanations

    MFMailComposeViewController canSendMail

    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
    ãģ¼ãģĨ
    -0.09
    asers
    -0.09
    lägg
    -0.09
    oyo
    -0.09
    koz
    -0.09
    -hide
    -0.08
    ä¸Ģéĥİ
    -0.08
    eldes
    -0.08
     اÙĦبا
    -0.08
    -toggler
    -0.08
    POSITIVE LOGITS
    æīįæľīåı¯èĥ½
    0.08
     compatibility
    0.08
     feasibility
    0.08
    亿
    0.08
    å¿ħé¡»åħĪ
    0.07
    å¿ħè¦ģ
    0.07
     prerequisite
    0.07
     Compatibility
    0.07
    åı¯è¡ĮæĢ§
    0.07
     prerequisites
    0.07
    Activations Density 0.038%

    No Known Activations