© 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. 51824
    Prev
    Next
    INDEX
    Explanations

    circuit, file extensions, libraries, technical terms

    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
    áb
    -0.08
    Würt
    -0.07
    _ALIGNMENT
    -0.07
    æĶ¾
    -0.07
    太大çļĦ
    -0.07
    ituto
    -0.07
    ebro
    -0.07
    太快
    -0.07
    ÃĤM
    -0.07
    aunch
    -0.07
    POSITIVE LOGITS
     itulah
    0.08
    并ç»ı
    0.07
     inilah
    0.07
     chứ
    0.07
    èĢĮä¸įæĺ¯
    0.07
    å®ŀå®ŀåľ¨åľ¨çļĦ
    0.07
     rather
    0.07
    çģ¿
    0.07
     irrespective
    0.07
    缴æݥ就
    0.07
    Activations Density 0.044%

    No Known Activations