© 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. 57820
    Prev
    Next
    INDEX
    Explanations

    rounding to decimal places

    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
    akon
    -0.08
     Äijẳng
    -0.08
    ãĥ©ãĥªãĥ¼
    -0.08
    fts
    -0.07
    entry
    -0.07
     Äijỡ
    -0.07
     wyt
    -0.07
     quit
    -0.07
    .files
    -0.07
    zem
    -0.07
    POSITIVE LOGITS
     rounding
    0.08
    åıĸèĪį
    0.08
    çĻ¾åĪĨ
    0.07
    ä¸ĩåĪĨ
    0.07
    æĪªåıĸ
    0.07
    Digits
    0.07
    çĻ¾äºº
    0.07
    ç§
    0.07
     trunc
    0.07
    æ¯į
    0.06
    Activations Density 0.021%

    No Known Activations