© 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. 2165
    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
    _ads
    -0.07
    ellate
    -0.07
    ä½¼
    -0.07
    emper
    -0.07
    ltra
    -0.07
    æķĻèĤ²åѦéĻ¢
    -0.07
    adol
    -0.07
    asher
    -0.07
    uja
    -0.06
     Sán
    -0.06
    POSITIVE LOGITS
     عÙĪض
    0.07
    ertet
    0.07
    RITE
    0.07
    ogg
    0.07
    ç¼
    0.07
    odik
    0.07
    å°Ķé¡¿
    0.06
    äºĨçĦ¶
    0.06
    ä½łæĿ¥
    0.06
    ÙĤاب
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.