© 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. 48831
    Prev
    Next
    INDEX
    Explanations

    microscopic analysis or simulation

    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
    æĸ½å·¥çļĦ
    -0.08
     shar
    -0.07
    ero
    -0.07
     ambi
    -0.07
    ãĤ·ãĥĥãĥĹ
    -0.07
    æĢİä¹ĪåĬŀåij¢
    -0.07
    åľ¨æĸ½å·¥
    -0.07
    æĢİä¹ĪåĬŀ
    -0.07
    شد
    -0.07
    orning
    -0.07
    POSITIVE LOGITS
    urna
    0.08
     models
    0.07
    解éĩĬäºĨ
    0.07
    模åŀĭ
    0.07
     partic
    0.07
     agitation
    0.07
     dart
    0.07
    ulong
    0.07
    åŁºæľ¬æ¦Ĥ念
    0.07
    adou
    0.07
    Activations Density 0.003%

    No Known Activations