© 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. 16239
    Prev
    Next
    INDEX
    Explanations

    diagonal matrix or form

    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
    æ·ĩ
    -0.08
    odox
    -0.07
    éb
    -0.07
    urio
    -0.07
    ibase
    -0.07
    æ¸
    -0.07
    åıĮåıĮ
    -0.07
    Abort
    -0.06
     Fior
    -0.06
    inol
    -0.06
    POSITIVE LOGITS
    éªĮèµĦ
    0.07
    ç«ĸåIJij
    0.07
    åĿIJä¸Ĭ
    0.07
    عÙĪ
    0.07
    ArrayOf
    0.07
     tallest
    0.07
     diag
    0.07
    diag
    0.07
    æĪijä¹Łåİ»
    0.07
    appoint
    0.07
    Activations Density 0.005%

    No Known Activations