© 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. 1271
    Prev
    Next
    INDEX
    Explanations

    rounding 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
    stag
    -0.08
    zinho
    -0.07
    bote
    -0.07
    uml
    -0.07
    acher
    -0.07
     Stär
    -0.07
    è¦ģéĹ»
    -0.07
    xel
    -0.07
    åĴĮæĸ¹æ³ķ
    -0.07
    aten
    -0.07
    POSITIVE LOGITS
    puted
    0.07
    ems
    0.07
    å°Ĩæķ´ä¸ª
    0.07
    feh
    0.06
    pec
    0.06
     Round
    0.06
    itti
    0.06
    ä¸įä¼ij
    0.06
     rounding
    0.06
     round
    0.06
    Activations Density 0.008%

    No Known Activations