© 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. 56718
    Prev
    Next
    INDEX
    Explanations

    legal or formal contexts

    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
    åĢºæĿĥä¿¡æģ¯
    -0.09
    çݰ代人
    -0.08
    gow
    -0.08
    æ³ķå¾ĭ声æĺİ
    -0.08
    ä¿¡çĶ¨è²¸æ¬¾
    -0.08
    åı¸æ³ķé£İéĻ©
    -0.08
    çī©ä»·å±Ģ
    -0.08
    åħ¬åı¸åĬ¨æĢģ
    -0.08
     дале
    -0.07
    abeth
    -0.07
    POSITIVE LOGITS
     pursuant
    0.11
     statutory
    0.09
     subparagraph
    0.09
    shall
    0.08
     provisions
    0.08
     derog
    0.08
     expressly
    0.08
    çļĦäºĭ项
    0.08
     waived
    0.08
     applicable
    0.08
    Activations Density 0.614%

    No Known Activations