© 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. 20755
    Prev
    Next
    INDEX
    Explanations

    development dependencies

    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
    undial
    -0.09
    ismatic
    -0.07
    ystems
    -0.07
    å¼ıçļĦ
    -0.07
    vij
    -0.06
    æł·çļĦ
    -0.06
    Subscriber
    -0.06
    产ä¸ļåŁºåľ°
    -0.06
    tabil
    -0.06
    мали
    -0.06
    POSITIVE LOGITS
    è¨Ĺ
    0.08
    amente
    0.07
    à¸ķà¹Ī
    0.07
    AccessType
    0.07
    鸦
    0.07
    éģ¿æļij
    0.07
    adle
    0.07
    Persistent
    0.06
    ä¸Ĭåĵģ
    0.06
    æĪijæĿ¥è¯´
    0.06
    Activations Density 0.002%

    No Known Activations