© 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. 57552
    Prev
    Next
    INDEX
    Explanations

    imaginary and complex numbers

    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
    icast
    -0.08
    anka
    -0.08
    zug
    -0.08
     Ulus
    -0.07
    å¾Ħ
    -0.07
    nage
    -0.07
    亿åIJ¨
    -0.07
    à¸Ķย
    -0.07
    太åı¤
    -0.07
    èĬ³
    -0.07
    POSITIVE LOGITS
    æIJħ
    0.07
    #error
    0.06
    éľī
    0.06
    çłĶåıijçļĦ
    0.06
    izzle
    0.06
    epen
    0.06
     Quaternion
    0.06
    bole
    0.06
     cent
    0.06
    é¡
    0.06
    Activations Density 0.010%

    No Known Activations