© 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. 48968
    Prev
    Next
    INDEX
    Explanations

    point X Y coordinates

    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
    åIJĮæŃ¥
    -0.07
    ä¸ŃæĪIJéķ¿
    -0.07
     brac
    -0.06
    éĥ½å¥½
    -0.06
    æĬ¥éģĵ称
    -0.06
    æĺ¥å¤©çļĦ
    -0.06
    èĢ¶
    -0.06
    terna
    -0.06
    ANY
    -0.06
    æį¢æĿ¥
    -0.06
    POSITIVE LOGITS
    .appendTo
    0.09
    缸åħ³éĹ®çŃĶ
    0.07
    åľ¨åĨħçļĦ
    0.07
     lies
    0.07
     ..."
    0.07
     belongs
    0.07
    åı£éķĩ
    0.07
     libur
    0.07
    ÑģÑĤин
    0.07
    ä¸įåľ¨
    0.07
    Activations Density 0.006%

    No Known Activations