© 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. 42040
    Prev
    Next
    INDEX
    Explanations

    scientific or mathematical names suffixes

    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
    åľ¨èĦ¸ä¸Ĭ
    -0.08
    SETS
    -0.08
    榻
    -0.08
    à¸Ļิ
    -0.08
    à¹Ģà¸Ķà¹ĩà¸Ķ
    -0.07
    uwen
    -0.07
    chette
    -0.07
    caffold
    -0.07
    PropertyName
    -0.07
     Tricks
    -0.07
    POSITIVE LOGITS
    azar
    0.07
    orter
    0.07
     Bas
    0.06
    åĪĨæŀIJäºĨ
    0.06
    åħ¬å¼ı
    0.06
    /simple
    0.06
    模åŀĭ
    0.06
     model
    0.06
     formula
    0.06
    /ip
    0.06
    Activations Density 0.002%

    No Known Activations