© 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. 23266
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions (sin, cos)

    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
    é¸¡æ¯Ľ
    -0.07
     DUP
    -0.07
    .ready
    -0.07
    emps
    -0.07
    gica
    -0.07
    åIJİè¿Ľ
    -0.07
    itora
    -0.07
    飦
    -0.07
     íĹĮ
    -0.07
    èĭ¦è¾£
    -0.07
    POSITIVE LOGITS
    inking
    0.07
    idores
    0.07
    ync
    0.07
    lob
    0.07
    HeaderView
    0.06
    wares
    0.06
     tra
    0.06
     ens
    0.06
    inh
    0.06
    INS
    0.06
    Activations Density 0.002%

    No Known Activations