© 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. 31677
    Prev
    Next
    INDEX
    Explanations

    medical, technical, or automotive terms

    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
    bers
    -0.08
    errat
    -0.08
    ÑĢоид
    -0.08
    è¡£é£Ł
    -0.07
    ples
    -0.07
    Ñĥжи
    -0.07
    éĺħ读åİŁæĸĩ
    -0.07
    ech
    -0.07
    루
    -0.07
    ÑĦи
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.09
    çŃīåIJĦæĸ¹éĿ¢
    0.08
    ä¹ŁæľīäºĨ
    0.07
    åľ¨è¿ĻäºĽ
    0.07
    ä¿¡æģ¯çŃī
    0.07
    opedia
    0.07
    åĴĮåŁºæľ¬
    0.07
    æѤæŶçļĦ
    0.07
    è¿ĻäºĽåĽłç´ł
    0.07
    åľ¨è¿Ļæł·çļĦ
    0.07
    Activations Density 0.231%

    No Known Activations