© 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. 33609
    Prev
    Next
    INDEX
    Explanations

    divisible by or tail of object

    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
    ezza
    -0.08
    дай
    -0.08
    olari
    -0.08
    è¡¡éĩı
    -0.07
    -platform
    -0.07
    ime
    -0.07
    Gran
    -0.07
    izon
    -0.07
    åIJĦæľīåIJĦ
    -0.07
    olare
    -0.07
    POSITIVE LOGITS
    确认åIJİ
    0.07
    ÑģлÑı
    0.07
    azzo
    0.06
     Dw
    0.06
    éľĩ
    0.06
     confirmed
    0.06
    .sent
    0.06
     Teixeira
    0.06
    å°ı鸡
    0.06
    æ¼ĵ
    0.06
    Activations Density 0.003%

    No Known Activations