© 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. 62950
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    __/
    -0.09
    aket
    -0.08
    uzz
    -0.08
    кок
    -0.08
    auer
    -0.07
    ×IJ×ķ
    -0.07
    deo
    -0.07
    åĨįä¸į
    -0.07
    icola
    -0.07
    åij±åij±
    -0.07
    POSITIVE LOGITS
    为åįķä½į
    0.07
     unit
    0.07
    unit
    0.07
    åįĺä½į
    0.07
    .rt
    0.06
    uhan
    0.06
     اÙĦÙĪا
    0.06
    æĹ¥ä»¥ä¸Ĭ
    0.06
     verse
    0.06
    /unit
    0.06
    Activations Density 0.004%

    No Known Activations