© 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. 45408
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or currency symbols

    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
    huri
    -0.08
    ListOf
    -0.07
    çħĮ
    -0.07
    æĭĽæłĩåħ¬åijĬ
    -0.07
    ÙİÙijا
    -0.06
    nock
    -0.06
    好æĥ³
    -0.06
    æĻ®åĪ©
    -0.06
     ÙĪØ£ÙĨÙĩ
    -0.06
    yed
    -0.06
    POSITIVE LOGITS
     pair
    0.08
    alej
    0.07
    pair
    0.07
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.07
    å·®ä¸į
    0.07
    çĥŃè¡·äºİ
    0.07
    ones
    0.07
    ä¸į符åIJĪ
    0.07
    _MAGIC
    0.07
    formular
    0.07
    Activations Density 0.018%

    No Known Activations