© 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. 42539
    Prev
    Next
    INDEX
    Explanations

    details, detail, details

    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
    oroz
    -0.08
    é³į
    -0.07
    ling
    -0.07
    临
    -0.07
    ubit
    -0.07
    arder
    -0.07
    ัà¸ģษà¹Į
    -0.07
    preter
    -0.07
    eri
    -0.07
    ahas
    -0.07
    POSITIVE LOGITS
    ota
    0.08
    ote
    0.07
    ekan
    0.07
    ä¸įå¾Ĺä¸į说
    0.07
    allee
    0.07
     Damas
    0.07
    å¼Ģ个
    0.06
    krim
    0.06
     Fora
    0.06
    -theme
    0.06
    Activations Density 0.033%

    No Known Activations