© 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. 29964
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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
    সà§įত
    -0.07
     обÑı
    -0.07
    è¯
    -0.07
    ÙĨÚ¯
    -0.07
    à¤ĸा
    -0.07
    ssa
    -0.07
    -txt
    -0.07
    isan
    -0.07
    tle
    -0.07
    ène
    -0.07
    POSITIVE LOGITS
    anst
    0.07
    tings
    0.07
    æľŁçļĦ
    0.06
    æľĪä¸Ĭ
    0.06
    omin
    0.06
     Klo
    0.06
    æĹłæŀģ
    0.06
    æķ´ä½ĵä¸Ĭ
    0.06
     proport
    0.06
    Acknowled
    0.06
    Activations Density 0.022%

    No Known Activations