© 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. 3054
    Prev
    Next
    INDEX
    Explanations

    double floating point numbers

    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
    çĪĨåĩº
    -0.09
    éģįéĩİ
    -0.08
    بÙĪر
    -0.08
    ä¼Ĺå¿ĹæĪIJ
    -0.08
    ediat
    -0.08
    çķªåı·
    -0.08
     numbering
    -0.07
    letz
    -0.07
    elé
    -0.07
    Į¨
    -0.07
    POSITIVE LOGITS
    .parseFloat
    0.10
    æµ®
    0.09
     floating
    0.08
     float
    0.08
    .toFixed
    0.08
    toFixed
    0.08
    .SetFloat
    0.08
     precision
    0.07
     Float
    0.07
    (float
    0.07
    Activations Density 0.095%

    No Known Activations