© 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. 46985
    Prev
    Next
    INDEX
    Explanations

    fiscal and financial periods

    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
    ahas
    -0.08
    åĩłç§ĴéĴŁ
    -0.08
    .times
    -0.07
    emos
    -0.07
    å°ıæŶåIJİ
    -0.07
    ÑĢоÑģа
    -0.07
    ierzch
    -0.07
    ectos
    -0.06
    æľĢä½İåѦåİĨ
    -0.06
    åĪ°åºķ
    -0.06
    POSITIVE LOGITS
     cycle
    0.11
    Cycle
    0.11
    -cycle
    0.10
     Cycle
    0.10
    cycle
    0.10
    åij¨æľŁ
    0.10
     period
    0.09
    _cycle
    0.09
    ãĤµãĤ¤ãĤ¯ãĥ«
    0.09
    åij¨æľŁçļĦ
    0.09
    Activations Density 0.095%

    No Known Activations