© 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. 48297
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and expressions

    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
    Ĺ
    -0.07
     ayrı
    -0.07
    ä»İä¸Ģ个
    -0.06
     olmayan
    -0.06
     Artes
    -0.06
    czyn
    -0.06
    ince
    -0.06
     Aufs
    -0.06
    éĻ¤ä»¥
    -0.06
    imoto
    -0.06
    POSITIVE LOGITS
    erre
    0.08
    pend
    0.08
    anni
    0.07
     sake
    0.07
    meg
    0.07
    ourg
    0.07
    iterals
    0.07
    etre
    0.07
    ä¸Ģ身
    0.07
    isir
    0.07
    Activations Density 0.008%

    No Known Activations