© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12418
    Prev
    Next
    INDEX
    Explanations

    below

    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
    emis
    -0.08
    ÑģнÑĥÑİ
    -0.08
    åİĭ
    -0.07
    ı
    -0.07
     zoals
    -0.07
     nagu
    -0.07
    人åķĬ
    -0.07
    çĿĢæĥ³
    -0.07
    rensa
    -0.07
    oline
    -0.07
    POSITIVE LOGITS
    ÙĪائ
    0.06
    udo
    0.06
    æĺĤ
    0.06
    åĵĶ
    0.06
     Suff
    0.06
    çłº
    0.06
    ä¸įæĢķ
    0.06
    寥
    0.06
    ada
    0.06
    пелÑĮ
    0.06
    Activations Density 0.073%

    No Known Activations