© 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. 14322
    Prev
    Next
    INDEX
    Explanations

    answers, colon, or check

    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
    ä»ĸæĺ¯ä¸Ģ个
    -0.09
    ellini
    -0.09
    æĪijæĦ¿æĦı
    -0.09
    urls
    -0.08
    ÚĺÛĮ
    -0.08
    ippo
    -0.08
    ót
    -0.08
    aidu
    -0.08
    ä½ķçŃī
    -0.08
    æĸĩåĮĸæĹħ游
    -0.08
    POSITIVE LOGITS
    ya
    0.06
     comment
    0.06
     calculations
    0.06
    æł¹æį®
    0.06
    çİī
    0.05
    ym
    0.05
    ä½
    0.05
    0.05
    1
    0.05
    .Completed
    0.05
    Activations Density 0.001%

    No Known Activations