© 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. 60273
    Prev
    Next
    INDEX
    Explanations

    little is known

    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
     conform
    -0.07
    оÑĤÑĮ
    -0.06
     Carta
    -0.06
    ostar
    -0.06
    åĩĨç¡®æĢ§åĴĮåIJĪæ³ķæĢ§
    -0.06
    ãģŁãģ¨
    -0.06
    оÑģÑĤа
    -0.06
    è¶Ĭ
    -0.06
    æĶ¯
    -0.06
    ç²ĹæĶ¾
    -0.06
    POSITIVE LOGITS
    ãģķãģĦ
    0.07
    ovnÃŃ
    0.07
    ILING
    0.07
    igny
    0.07
    ä»Ĭå¤©åľ¨
    0.07
    ilin
    0.07
    quisite
    0.07
    pth
    0.07
    пли
    0.07
    è´ŀ
    0.06
    Activations Density 0.605%

    No Known Activations