© 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. 28468
    Prev
    Next
    INDEX
    Explanations

    function, names, maternity, ads, applications

    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
    oya
    -0.06
    ä½łçļĦæľĭåıĭ
    -0.06
    éĶĻ
    -0.06
    íĺ¼
    -0.06
    ovich
    -0.06
    -version
    -0.06
    AAF
    -0.06
    ai
    -0.06
    asca
    -0.06
    quir
    -0.06
    POSITIVE LOGITS
    è¡Ģä¸Ŀ
    0.08
    ÑĨо
    0.08
    社åĨħ
    0.08
    urato
    0.08
    سÙĪ
    0.07
    WithType
    0.07
    agon
    0.07
    ết
    0.07
    apel
    0.07
     Baghd
    0.07
    Activations Density 0.302%

    No Known Activations