© 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. 28688
    Prev
    Next
    INDEX
    Explanations

    lazy initialization

    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
    åı¤ä»Ĭ
    -0.08
    顾
    -0.08
    åĬ©æīĭ
    -0.07
    ventus
    -0.07
    vey
    -0.07
     diku
    -0.07
    vl
    -0.07
    è´¯
    -0.07
    åĬ©
    -0.07
    横
    -0.07
    POSITIVE LOGITS
     lazy
    0.12
    lazy
    0.11
     deferred
    0.10
     laz
    0.10
    æĮīéľĢ
    0.10
     triggered
    0.09
     Lazy
    0.09
     Trigger
    0.09
    Lazy
    0.09
    Deferred
    0.09
    Activations Density 0.133%

    No Known Activations