© 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. 17272
    Prev
    Next
    INDEX
    Explanations

    casting and type conversion

    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
    æĢ§åŃIJ
    -0.07
    åİŁåľ°
    -0.06
     last
    -0.06
    mond
    -0.06
     "
    -0.06
    last
    -0.06
     catalog
    -0.06
    èĹı
    -0.06
    Rew
    -0.06
     remote
    -0.06
    POSITIVE LOGITS
    _cast
    0.10
    acades
    0.09
    CastException
    0.09
    FromString
    0.09
    ellation
    0.09
    uala
    0.09
    _CAST
    0.09
    .cast
    0.09
    ToInt
    0.09
     kedalam
    0.09
    Activations Density 0.038%

    No Known Activations