© 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. 64733
    Prev
    Next
    INDEX
    Explanations

    function definition

    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
    èĮ¶é¦Ļ
    -0.06
    ä¾ĥ
    -0.06
    代è¨Ģ
    -0.06
    veu
    -0.06
    ableView
    -0.06
    ãĤ¤ãĥ«
    -0.06
    Ñģлей
    -0.06
    ilog
    -0.06
     racked
    -0.06
    渺
    -0.06
    POSITIVE LOGITS
    è¿Ŀç«ł
    0.08
    éĺ²å¤ĩ
    0.07
    ma
    0.07
    à¹īà¸ĩ
    0.07
    以éĺ²
    0.07
    ollo
    0.07
     dropout
    0.07
    ãĤ¬ãĥ¼ãĥī
    0.07
    texte
    0.07
    çł´æµª
    0.06
    Activations Density 0.332%

    No Known Activations