© 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. 41139
    Prev
    Next
    INDEX
    Explanations

    declaring arrays and objects

    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
    loff
    -0.08
    ä¸įäºĨçļĦ
    -0.08
    startswith
    -0.07
     Fet
    -0.07
    å·²ç»ıè¿ĩåİ»
    -0.07
    üs
    -0.07
    ples
    -0.07
    åĪĨéĴ±
    -0.07
    à¸Īารยà¹Į
    -0.07
     Wich
    -0.07
    POSITIVE LOGITS
    onga
    0.07
    åľĪ
    0.06
    æĸ¹ä¾¿
    0.06
    åIJĮ
    0.06
    unte
    0.06
    çIJĨ
    0.06
    irut
    0.06
    佬
    0.06
    unts
    0.06
    ắp
    0.06
    Activations Density 0.006%

    No Known Activations