© 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. 39461
    Prev
    Next
    INDEX
    Explanations

    numbers or punctuation followed by specific words

    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
    alin
    -0.07
    ç»ıåħ¸çļĦ
    -0.06
    ®,
    -0.06
    orgia
    -0.06
    åĸ§
    -0.06
    ä¸įåİĮ
    -0.06
    èµ·æīĭ
    -0.06
    /../
    -0.06
    olin
    -0.06
    ali
    -0.06
    POSITIVE LOGITS
    ÙĦÙĪÙĦ
    0.09
    å°ıå°ı
    0.08
    ูล
    0.08
    åıĤèĢĥä»·æł¼
    0.08
    å°ı家ä¼Ļ
    0.08
    è¿Ļ个å°ı
    0.08
    Õ©
    0.07
    .xyz
    0.07
    filesize
    0.07
    sville
    0.07
    Activations Density 0.058%

    No Known Activations