© 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. 42782
    Prev
    Next
    INDEX
    Explanations

    numbers, symbols, and mathematical 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
     Conv
    -0.07
    onde
    -0.07
    ools
    -0.07
    åĨĽåľ¨
    -0.07
    (script
    -0.06
    обÑĢа
    -0.06
    war
    -0.06
    ward
    -0.06
    èŀºä¸Ŀ
    -0.06
    被ç½ļ
    -0.06
    POSITIVE LOGITS
    andler
    0.10
    .sym
    0.07
    structor
    0.07
     kall
    0.07
    IOC
    0.07
    Фо
    0.07
    åij¼
    0.07
    isor
    0.07
    quel
    0.07
     cint
    0.07
    Activations Density 0.003%

    No Known Activations