© 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. 17745
    Prev
    Next
    INDEX
    Explanations

    jsfiddle.net/

    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
    ³
    -0.07
    æĪijåIJ§
    -0.07
    awan
    -0.06
    utsch
    -0.06
     Ñģалоне
    -0.06
     M
    -0.06
    Attributes
    -0.06
    arts
    -0.05
    è¿Ļä¸ªæł·åŃIJ
    -0.05
    getApplication
    -0.05
    POSITIVE LOGITS
    æīĢåIJij
    0.07
     tÃł
    0.07
    åѦéĩij
    0.07
     darum
    0.07
    æĬĢæľ¯ä¸İ
    0.07
    åĬªåĬĽæıIJé«ĺ
    0.07
    ainers
    0.07
    驻马
    0.07
    ç«ĭå¿Ĺ
    0.07
    ddb
    0.07
    Activations Density 0.007%

    No Known Activations