© 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. 42921
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ton
    -0.07
    toa
    -0.06
    å¤Ń
    -0.06
    æıª
    -0.06
    ़
    -0.06
     tutta
    -0.06
    该åī§
    -0.06
    ä¸įå°½
    -0.06
    è¿ŀ带
    -0.06
    ਣ
    -0.06
    POSITIVE LOGITS
    æ°´åĻ¨
    0.08
    å°±åģļ
    0.08
    istou
    0.08
    à·ĥà·Ĭ
    0.07
    æ¦Ī
    0.07
    è¿ĶãģĹ
    0.07
     fisheries
    0.07
    ÙĨدÙĩ
    0.07
    attes
    0.07
    @student
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.