© 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. 32266
    Prev
    Next
    INDEX
    Explanations

    primary followed by a noun

    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
    ../../../
    -0.11
    ../
    -0.11
    ä¼ĹæīĢåij¨çŁ¥
    -0.10
    ÑĢегÑĥли
    -0.09
    à§Ģয়
    -0.09
     Istitu
    -0.09
    çĻ¾å·Ŀ
    -0.09
    nish
    -0.09
    ouvelle
    -0.09
    ypes
    -0.08
    POSITIVE LOGITS
    ity
    0.11
    ordial
    0.09
    åĴĮ第äºĮ
    0.07
    缮çļĦæĺ¯
    0.07
    ä½ľçĶ¨æĺ¯
    0.07
    /
    0.06
    次çļĦ
    0.06
     gauche
    0.06
    uddin
    0.06
    ¸
    0.06
    Activations Density 0.037%

    No Known Activations