© 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. 12970
    Prev
    Next
    INDEX
    Explanations

    parsing, decoding, deserialization

    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
     putchar
    -0.07
    .writ
    -0.07
    _idle
    -0.07
     Carter
    -0.06
     purs
    -0.06
    arki
    -0.06
    åĨħ容æıIJä¾Ľæĸ¹
    -0.06
    _putchar
    -0.06
    æİĴæĶ¾éĩı
    -0.06
    GenerationStrategy
    -0.06
    POSITIVE LOGITS
     parsing
    0.14
    解æŀIJ
    0.13
     parses
    0.12
    解çłģ
    0.12
    _convert
    0.12
     conversions
    0.12
     decoding
    0.12
    _PARSE
    0.12
    转æį¢
    0.12
     decode
    0.12
    Activations Density 0.458%

    No Known Activations