© 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. 39876
    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
    족
    -0.09
    ||(
    -0.08
     REALLY
    -0.07
    è¿ĻäºĽè¯Ŀ
    -0.07
    .ui
    -0.07
    ê³Ħê°Ģ
    -0.07
    cardo
    -0.07
    Ñľ
    -0.07
    à¹Ģà¸ŀ
    -0.07
    æ¡¥éķĩ
    -0.07
    POSITIVE LOGITS
    è¶Ł
    0.07
    enheim
    0.07
    iev
    0.07
    itches
    0.07
     conjoint
    0.07
    bud
    0.06
    æ½¢
    0.06
    -addon
    0.06
     beard
    0.06
    éĤ£æł·çļĦ
    0.06
    Activations Density 0.000%

    No Known Activations