© 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. 928
    Prev
    Next
    INDEX
    Explanations

    evaluating numbers or fractions

    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
    hec
    -0.09
    hek
    -0.08
    nable
    -0.08
    æĥŁæľī
    -0.08
    alion
    -0.08
    angun
    -0.08
    èĬ±èIJ½
    -0.08
    keiten
    -0.08
    æĺ¥æļĸ
    -0.07
    lice
    -0.07
    POSITIVE LOGITS
    æ©¡
    0.07
    valu
    0.07
    rou
    0.07
    é¢Ĥ
    0.06
    ä¿ĥè¿Ľä¼ļ
    0.06
    رج
    0.06
    ÑıÑģ
    0.06
    ä¸ĩå²ģ
    0.06
    éªı
    0.06
    uv
    0.06
    Activations Density 0.015%

    No Known Activations