© 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. 16480
    Prev
    Next
    INDEX
    Explanations

    left side expressions or assignments

    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
    ä¸Ĭæ¦ľ
    -0.07
    è´Ń
    -0.07
    ermann
    -0.07
    åµĮ
    -0.07
     "{"
    -0.07
    داد
    -0.06
    åľ¨ç»Ļ
    -0.06
    preh
    -0.06
    ooth
    -0.06
    æķħéĩĮ
    -0.06
    POSITIVE LOGITS
    _GUI
    0.07
    _DLL
    0.07
    hati
    0.07
    å°ı鬼
    0.07
     excuse
    0.06
    æħµ
    0.06
    ELE
    0.06
    éĽĨèģļ
    0.06
    icap
    0.06
    åĪĽå»ºäºİ
    0.06
    Activations Density 0.001%

    No Known Activations