© 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. 13673
    Prev
    Next
    INDEX
    Explanations

    initialization and constructor

    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
    DisplayName
    -0.07
    ä¸į离
    -0.06
     trần
    -0.06
    èķĬ
    -0.06
    ä¸įå¤ĸ
    -0.06
    ahui
    -0.06
     plural
    -0.06
    红å°ĺ
    -0.06
    ä¸į符
    -0.06
    ä¸įéĻIJäºİ
    -0.06
    POSITIVE LOGITS
    initialized
    0.13
     initializing
    0.13
     initialized
    0.13
    åĪĿå§ĭ
    0.13
     initialised
    0.13
     initializes
    0.13
    åĪĿå§ĭåĮĸ
    0.13
     initialize
    0.13
     Initializing
    0.12
     initialise
    0.12
    Activations Density 0.213%

    No Known Activations