© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27109
    Prev
    Next
    INDEX
    Explanations

    C/C++ header files

    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
    urr
    -0.06
    /
    -0.06
    æĪİ
    -0.06
    ieh
    -0.06
    etr
    -0.06
    è¿IJ
    -0.06
    aste
    -0.06
    åı¯ä¿¡
    -0.05
    /cli
    -0.05
    ega
    -0.05
    POSITIVE LOGITS
    ủng
    0.09
    оÑģо
    0.08
    ±
    0.08
    á»Ļp
    0.08
    ÙĬرات
    0.08
    nds
    0.08
    _aliases
    0.08
    ëį°ë¯¸
    0.08
    инÑĭ
    0.08
    kir
    0.08
    Activations Density 0.254%

    No Known Activations