© 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. 27439
    Prev
    Next
    INDEX
    Explanations

    calculating with integers and variables

    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
    æľīæĿĥä¿ĿçķĻ
    -0.08
     Garan
    -0.07
    å±ħåīį
    -0.07
    :Object
    -0.06
    æĸ¹å¼ı使çĶ¨
    -0.06
    uka
    -0.06
    éĽ¾
    -0.06
    ukka
    -0.06
    ,:,:
    -0.06
    å¿Ĺ强
    -0.06
    POSITIVE LOGITS
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
     deviation
    0.07
    _integer
    0.07
    anat
    0.07
    åľ°ä¸ĭåŁİ
    0.07
    æķ°ä¸ĩ
    0.07
    allen
    0.07
    oleon
    0.07
    æķ´æķ°
    0.07
    ÑħÑĢо
    0.06
    Activations Density 0.009%

    No Known Activations