© 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. 46717
    Prev
    Next
    INDEX
    Explanations

    formulas and existing structures

    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
    æŶæĹ¥
    -0.07
    æĺ¥ç¬ĭ
    -0.07
     chron
    -0.07
    èĤ¤èī²
    -0.07
    LOGGER
    -0.06
    InnerHTML
    -0.06
     пÑĢиÑħо
    -0.06
    Ø´ÙĬØ©
    -0.06
    StringRef
    -0.06
    _destroy
    -0.06
    POSITIVE LOGITS
    åħ¬å¼ı
    0.10
     formula
    0.09
     formulas
    0.09
     schematic
    0.08
    æ¡Ĩæŀ¶
    0.08
    formula
    0.08
     framework
    0.08
    æŀ¶
    0.08
     conceptual
    0.08
    ç»ĵæŀĦ设计
    0.08
    Activations Density 0.351%

    No Known Activations