© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50314
    Prev
    Next
    INDEX
    Explanations

    first occurrence

    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
    çļĦéĤ£äºĽ
    -0.07
    æ¯Ķä½ł
    -0.07
    @include
    -0.07
    åģıåģı
    -0.07
    åIJĪçIJĨæĢ§
    -0.07
    _UL
    -0.07
     yourselves
    -0.06
    ä¸ĸçķĮä¸ĬæľĢ大çļĦ
    -0.06
    为ç¥ĸåĽ½
    -0.06
    å°±æĺ¯åĽłä¸º
    -0.06
    POSITIVE LOGITS
    .workspace
    0.07
    ç¹¼
    0.07
    bedo
    0.07
     salvo
    0.07
    èĨĬ
    0.07
    lyn
    0.07
    åĦĢ
    0.07
    illac
    0.06
    é¾Ħ
    0.06
     ÑģÑĤолÑĮ
    0.06
    Activations Density 0.735%

    No Known Activations