© 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. 30005
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    ondo
    -0.06
    âm
    -0.06
    æĻĹ
    -0.06
    èĻļ空
    -0.06
    erna
    -0.06
    extern
    -0.06
    大èĢĮ
    -0.06
    çļĦå°ıåĮº
    -0.06
    lem
    -0.06
    秣
    -0.06
    POSITIVE LOGITS
    ighted
    0.07
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.07
    lius
    0.07
    ãģ«æ®ĭ
    0.07
    aler
    0.07
    orsz
    0.07
    nios
    0.07
    bral
    0.07
    quier
    0.07
    eref
    0.07
    Activations Density 0.002%

    No Known Activations