© 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. 20594
    Prev
    Next
    INDEX
    Explanations

    special mathematical symbols

    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
    ement
    -0.08
    exual
    -0.08
    fatt
    -0.08
     mạc
    -0.07
    landen
    -0.07
    erais
    -0.07
    оло
    -0.07
    ements
    -0.07
    اÙĩ
    -0.07
    íİĻ
    -0.07
    POSITIVE LOGITS
    oja
    0.09
    uÃŁ
    0.09
    aar
    0.08
    uwe
    0.08
    er
    0.08
    Ùĩ
    0.08
    ¤
    0.08
    riz
    0.08
    oop
    0.08
    ±
    0.07
    Activations Density 0.013%

    No Known Activations