© 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. 49092
    Prev
    Next
    INDEX
    Explanations

    precision and rounding

    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
    æľīæŶåĢĻ
    -0.07
    åIJ¬ä¸įæĩĤ
    -0.06
    çģµæ´»çļĦ
    -0.06
     classified
    -0.06
    æĶ¹åIJį
    -0.06
    管å±Ģ
    -0.06
     categorized
    -0.06
    åģ¶å°Ķ
    -0.06
     category
    -0.06
     traff
    -0.06
    POSITIVE LOGITS
    é«ĺ精度
    0.12
    精度
    0.11
    é«ĺç²¾
    0.11
    precision
    0.11
    精度é«ĺ
    0.10
    Precision
    0.10
    digits
    0.10
     digits
    0.10
     precision
    0.10
    .precision
    0.09
    Activations Density 0.008%

    No Known Activations