© 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. 45828
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and concepts

    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
    aseline
    -0.08
    éĢļ车
    -0.08
     ës
    -0.07
    emean
    -0.07
    ãĥĹãĥĪ
    -0.07
    orea
    -0.07
    luent
    -0.07
     Æ°ng
    -0.07
    ç§ijåŃ¦å®¶
    -0.07
     terpent
    -0.07
    POSITIVE LOGITS
    éĩİ
    0.07
    finite
    0.07
    FE
    0.06
    æĢ»ä¸įèĥ½
    0.06
    auta
    0.06
     presup
    0.06
     sem
    0.06
    .thread
    0.06
     valide
    0.06
     computing
    0.06
    Activations Density 0.013%

    No Known Activations