© 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. 42709
    Prev
    Next
    INDEX
    Explanations

    complex operator or PID, cyclic, dimensional, open, compact, rooted

    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
    ÛĮات
    -0.08
     diket
    -0.08
    ippi
    -0.08
    ÙĨاÙĦ
    -0.07
    ä¸ºåĽ½
    -0.07
    å¾Ĺ人
    -0.07
    ä¹ĭåīij
    -0.07
    äºĮéĨĩ
    -0.07
    åĩłå£°
    -0.07
    iby
    -0.07
    POSITIVE LOGITS
     anywhere
    0.08
    ä¸įéľĢè¦ģ
    0.08
    ä¸įéľĢ
    0.07
    æĹłéľĢ
    0.07
    ä¸įæĦģ
    0.07
    orsch
    0.07
    çī¹æľīçļĦ
    0.07
     everywhere
    0.07
     scher
    0.06
    æĹłè®º
    0.06
    Activations Density 0.038%

    No Known Activations