© 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. 42424
    Prev
    Next
    INDEX
    Explanations

    electrodes and plates

    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
    å¼¹åĩºçļĦ
    -0.09
    ombe
    -0.08
     dorm
    -0.08
    å²Ĺ
    -0.08
    çĿ¡è¢ĭ
    -0.07
    ikian
    -0.07
    个人æĪĸ
    -0.07
     arity
    -0.07
    _INV
    -0.07
    omore
    -0.07
    POSITIVE LOGITS
     capacitor
    0.09
     capacit
    0.09
    çĶµå®¹åĻ¨
    0.08
     between
    0.08
     filled
    0.08
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.08
    éļĶ
    0.08
    缸è·Ŀ
    0.08
    éļĶæĸŃ
    0.08
    éļĶå¼Ģ
    0.08
    Activations Density 0.019%

    No Known Activations