© 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. 42392
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and calculus

    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
    ÃīG
    -0.09
    羣å¿ĥçļĦ
    -0.08
    auff
    -0.08
     esecuzione
    -0.08
    frauen
    -0.07
    _batches
    -0.07
    à°Ĥà°Ł
    -0.07
    ìĦ¸
    -0.07
    маÑĢа
    -0.07
    erta
    -0.07
    POSITIVE LOGITS
    åĻ
    0.08
    ä»ĸ身ä¸Ĭ
    0.07
    åĢĻ
    0.07
    侯
    0.07
    人åħ³æ³¨
    0.07
    uhl
    0.06
    Separator
    0.06
    å½±
    0.06
    æľĭ
    0.06
    çģ¶
    0.06
    Activations Density 0.009%

    No Known Activations