© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48470
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    被åŃIJ
    -0.07
    usin
    -0.07
    ÑĢек
    -0.07
    åIJįå°Ĩ
    -0.07
    atrices
    -0.07
    hini
    -0.07
    érée
    -0.07
    aidu
    -0.06
    atrix
    -0.06
    dev
    -0.06
    POSITIVE LOGITS
    çĮ®
    0.08
     karÅŁ
    0.07
    对åºĶçļĦ
    0.07
     Ñģловом
    0.07
     BEST
    0.07
     colloc
    0.07
    ube
    0.07
    Ç
    0.07
    åĭŁ
    0.07
    à¸Ħำวà¹Īา
    0.07
    Activations Density 0.064%

    No Known Activations