© 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. 20640
    Prev
    Next
    INDEX
    Explanations

    max or maximum values

    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
    æ±°
    -0.07
    à¹Ģรียà¸ļรà¹īà¸Ńย
    -0.07
     Mell
    -0.07
    ÑĪеÑĤ
    -0.07
    anam
    -0.07
    ÙĪÙħت
    -0.07
    äºķåĨĪ
    -0.07
    éķ¿éĿĴ
    -0.06
    UFF
    -0.06
     Relief
    -0.06
    POSITIVE LOGITS
     max
    0.15
    (max
    0.14
     Max
    0.14
    max
    0.14
    .max
    0.13
     maximum
    0.13
    æľĢ大
    0.13
    çļĦæľĢ大
    0.13
    -max
    0.13
    _max
    0.12
    Activations Density 0.008%

    No Known Activations