© 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. 39704
    Prev
    Next
    INDEX
    Explanations

    intersection of geometric shapes

    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
    oldt
    -0.08
    engo
    -0.07
    elar
    -0.06
    å¿Į
    -0.06
    éĤ£åº§
    -0.06
    ellä
    -0.06
    è¯Ŀ
    -0.06
     afterwards
    -0.06
    æIJĤ
    -0.06
    èĢģåİ»
    -0.06
    POSITIVE LOGITS
    IBA
    0.08
    strup
    0.08
    atsby
    0.08
    æĻ¨
    0.08
    ä¹ĭä¸Ģæĺ¯
    0.08
    ä¹ĭä¸ĢçļĦ
    0.07
    å¤įæ£Ģ
    0.07
    ÑģÑĤÑı
    0.07
    è´°
    0.07
     sod
    0.07
    Activations Density 0.004%

    No Known Activations