© 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. 30990
    Prev
    Next
    INDEX
    Explanations

    frequency and timing

    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
    деÑĢа
    -0.08
    æľĢå¾Įãģ¾ãģ§
    -0.07
    ÑĦина
    -0.07
    abyrinth
    -0.07
     enx
    -0.07
    онеÑĢа
    -0.07
    å°ıçļĦæŶåĢĻ
    -0.07
    ä¸Ĭ课æŶ
    -0.07
    jern
    -0.07
    _trap
    -0.07
    POSITIVE LOGITS
    é¢ijçİĩ
    0.18
     frequency
    0.16
     Frequency
    0.14
    éł»çİĩ
    0.14
    é¢ij次
    0.14
    çļĦé¢ijçİĩ
    0.14
    éł»
    0.13
    frequency
    0.13
    Frequency
    0.13
    _frequency
    0.12
    Activations Density 0.102%

    No Known Activations