© 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. 55961
    Prev
    Next
    INDEX
    Explanations

    normal distribution pdf

    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
     Amat
    -0.09
    endant
    -0.08
    ulat
    -0.08
    ULK
    -0.08
    æĢ»æĬķèµĦ
    -0.08
    odat
    -0.07
    á»Ļc
    -0.07
    isman
    -0.07
    umer
    -0.07
    没æľīæŶéĹ´
    -0.07
    POSITIVE LOGITS
    ogne
    0.08
    æłĩåĩĨåĮĸ
    0.07
     Ney
    0.07
     sin
    0.07
     gaussian
    0.07
    èĭĹ
    0.07
    ico
    0.07
    aussian
    0.07
     distribution
    0.07
    oi
    0.07
    Activations Density 0.003%

    No Known Activations