© 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. 61367
    Prev
    Next
    INDEX
    Explanations

    changes and updates

    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
    Õ¡Õ½
    -0.07
     choc
    -0.07
    asso
    -0.07
    顺åĪ©å¼Ģå±ķ
    -0.07
    ffet
    -0.07
    fq
    -0.07
    çĥŃéŨæIJľç´¢
    -0.07
    Outside
    -0.06
    ä¸ĭä¸ĢæŃ¥
    -0.06
    çļĦ建ç«ĭ
    -0.06
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.12
     modifications
    0.12
    çīĪæľ¬
    0.12
    å®ĮåĸĦ
    0.11
     versions
    0.11
     tweaks
    0.11
    çīĪ
    0.11
     version
    0.11
    ä¿®æĶ¹
    0.11
    修订
    0.11
    Activations Density 0.465%

    No Known Activations