© 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. 45296
    Prev
    Next
    INDEX
    Explanations

    .floor, integer, toInt

    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
     Mancha
    -0.08
    ç³»çļĦ
    -0.08
    åѦæ³ķ
    -0.07
    reis
    -0.07
    mans
    -0.07
     spotlight
    -0.07
    FIELDS
    -0.07
     chè
    -0.07
    stoff
    -0.07
    éĹ»åĪ°
    -0.07
    POSITIVE LOGITS
    .floor
    0.08
     integer
    0.08
    floor
    0.08
     floor
    0.08
     floors
    0.08
    toInt
    0.08
    æķ´
    0.07
    æ±ŁåŁİ
    0.07
    æķ´æķ°
    0.07
    ä¸įä¸ĭ
    0.07
    Activations Density 0.004%

    No Known Activations