© 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. 63970
    Prev
    Next
    INDEX
    Explanations

    candidates for selection

    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
    æ²³éķĩ
    -0.08
    è·¯éĢı
    -0.08
    oscope
    -0.07
    é²ģçıŃ
    -0.07
    女éĥİ
    -0.07
    รุ
    -0.07
    ĮĢ
    -0.07
     wohl
    -0.07
    éĥ¨åĪĨåĨħ容
    -0.07
    abilia
    -0.06
    POSITIVE LOGITS
    ׳×Ļ×Ķ
    0.07
    AMILY
    0.07
     Laz
    0.07
    _tuple
    0.07
    éĻĦçĿĢ
    0.07
    å¯Ĩå¸ĥ
    0.07
    åĮĸåIJĪ
    0.06
    ingleton
    0.06
    æĻº
    0.06
    icky
    0.06
    Activations Density 0.002%

    No Known Activations