© 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. 10188
    Prev
    Next
    INDEX
    Explanations

    mathematical expression delimiters

    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
    -
    -0.06
    çĴŀ
    -0.06
    6
    -0.06
    cko
    -0.06
     aqu
    -0.06
    rag
    -0.06
    odu
    -0.06
    سÙĩ
    -0.06
    9
    -0.05
    owo
    -0.05
    POSITIVE LOGITS
    imentary
    0.09
    baugh
    0.09
    Powered
    0.08
    oard
    0.08
    à¸Ĺุ
    0.08
     Powered
    0.08
    åħ·ä½ĵæŶéĹ´
    0.08
    øver
    0.08
    .reverse
    0.08
    ège
    0.08
    Activations Density 0.003%

    No Known Activations