© 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. 11897
    Prev
    Next
    INDEX
    Explanations

    single, year, month, day

    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
    incar
    -0.08
    plin
    -0.08
    onnant
    -0.07
    æľīæķĪæľŁèĩª
    -0.07
     auseinander
    -0.07
    æĹ¥æľĪ
    -0.07
    AKAN
    -0.07
    isz
    -0.07
    _hooks
    -0.07
    isar
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.12
    (s
    0.10
    æĪĸå¤ļ
    0.09
     ÙĪاØŃدة
    0.08
     single
    0.08
    åıĪä¸Ģ
    0.08
     SINGLE
    0.08
    åıĪä¸Ģ个
    0.08
    /single
    0.08
     tunggal
    0.07
    Activations Density 0.248%

    No Known Activations