© 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. 33284
    Prev
    Next
    INDEX
    Explanations

    quantity (number + unit)

    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
    unda
    -0.06
    ↵
    -0.06
    ardo
    -0.06
    æħ°
    -0.06
    ÑĤов
    -0.06
    -0.06
    jen
    -0.06
     |
    -0.06
    —
    -0.06
    PER
    -0.06
    POSITIVE LOGITS
    亮é»ŀ
    0.08
    à¸ŀà¸Ńà¸Ķี
    0.08
    家åºĹ
    0.08
    è¡Ĺåı£
    0.08
    IMATE
    0.08
    osso
    0.08
    ãģ¨ãģĦãģĪãģ°
    0.08
    ãģ«ãģĤãģŁ
    0.08
    _named
    0.08
    ạch
    0.07
    Activations Density 0.038%

    No Known Activations