© 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. 31291
    Prev
    Next
    INDEX
    Explanations

    adhere to rules and principles

    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
    вина
    -0.09
    оÑĢа
    -0.08
    wares
    -0.08
    æĶ¯æĮģåĬĽåº¦
    -0.08
    åĴĮè§ĦèĮĥ
    -0.07
    zeuge
    -0.07
    à¹Ħà¸ģล
    -0.07
    Õ¡Õµ
    -0.07
     permanente
    -0.07
    zeug
    -0.07
    POSITIVE LOGITS
    ä¸¥æł¼çļĦ
    0.10
    交éĢļè§ĦåĪĻ
    0.09
    çļĦåİŁåĪĻ
    0.09
     strict
    0.09
    诺è¨Ģ
    0.09
    æĹ¢å®ļ
    0.09
     principles
    0.09
    åŁºæľ¬åİŁåĪĻ
    0.08
     rules
    0.08
    ä¸įæ¸Ŀ
    0.08
    Activations Density 0.071%

    No Known Activations