© 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. 2660
    Prev
    Next
    INDEX
    Explanations

    angle degrees

    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
    ruk
    -0.08
    -stars
    -0.08
     plasti
    -0.07
     besti
    -0.07
     Yellowstone
    -0.07
    åĽ´ç»ķçĿĢ
    -0.07
    æĥ³å°½
    -0.07
    æ¯ĶæĪij
    -0.07
    å·¥ä½ľå®īæİĴ
    -0.07
    à¸ģล
    -0.07
    POSITIVE LOGITS
     Piper
    0.07
    pac
    0.07
    æĸľéĿ¢
    0.07
    çļĦèµ°åĬ¿
    0.06
    åĨĽåĽ¢
    0.06
    eler
    0.06
    缸åħ³éĵ¾æİ¥
    0.06
    Leg
    0.06
    Vision
    0.06
    人æ°ij群ä¼ĹçļĦ
    0.06
    Activations Density 0.007%

    No Known Activations