© 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. 48787
    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
    æµĴ
    -0.07
    大å±Ģ
    -0.07
    æĬ¥
    -0.06
    ohn
    -0.06
    æĪIJåħ¨
    -0.06
    ooled
    -0.06
    éĵº
    -0.06
    riv
    -0.06
    jen
    -0.06
    urban
    -0.06
    POSITIVE LOGITS
    طار
    0.08
     ""),
    0.08
    Ùİض
    0.08
    bia
    0.08
    æľ¬æĿ¥
    0.08
    eppe
    0.08
     '');
    0.07
    STALL
    0.07
    累累
    0.07
    æ¶Ļ
    0.07
    Activations Density 0.000%

    No Known Activations