© 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. 17548
    Prev
    Next
    INDEX
    Explanations

    animals, vehicles, and commerce

    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
    à¹Ģà¸ģลà¹īา
    -0.08
    nell
    -0.07
    heimer
    -0.07
    ä¸ĢæĪIJ
    -0.07
    ä¸ĢèĪ¬æľī
    -0.07
    çĤ¬
    -0.07
    moz
    -0.07
    että
    -0.07
    loid
    -0.07
    PROFILE
    -0.07
    POSITIVE LOGITS
     Porter
    0.07
    æ¼Ķ讲稿
    0.06
    achu
    0.06
    oms
    0.06
    讲
    0.06
    -space
    0.06
    åĮ
    0.06
     Slam
    0.06
    _DISPATCH
    0.06
    èĴĻ
    0.06
    Activations Density 0.001%

    No Known Activations