© 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. 51807
    Prev
    Next
    INDEX
    Explanations

    comparison operators and values

    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
    alloc
    -0.08
    erts
    -0.07
     Kirk
    -0.07
    大éĩij
    -0.07
    æ´Ľä¼Ĭ
    -0.07
    æľĪåľĨ
    -0.07
    人åħ³æ³¨
    -0.07
    _tool
    -0.07
    ä¸İçİ°å®ŀ
    -0.07
    豪
    -0.07
    POSITIVE LOGITS
    åľ¨åħĪ
    0.08
    SearchParams
    0.07
     Mondial
    0.07
    alous
    0.07
    aller
    0.06
    agli
    0.06
    ç¿ĺ
    0.06
    对æĸ¹çļĦ
    0.06
     جست
    0.06
    ä¹ĭè¾Ī
    0.06
    Activations Density 0.006%

    No Known Activations