© 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. 17482
    Prev
    Next
    INDEX
    Explanations

    sizeof, offsetof, alignment

    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
    steller
    -0.10
    èĶ«
    -0.08
     UIL
    -0.08
    çĶĦ
    -0.08
    弩
    -0.08
    eby
    -0.08
    çĸĨ
    -0.07
    éļĪ
    -0.07
     NDEBUG
    -0.07
    æĩ¸
    -0.07
    POSITIVE LOGITS
     sizeof
    0.10
     offsetof
    0.09
    _alignment
    0.08
    sizeof
    0.08
    offsetof
    0.08
    (sizeof
    0.08
     offsets
    0.07
     Integrity
    0.07
    å¸ĥå±Ģ
    0.07
     Alignment
    0.07
    Activations Density 0.115%

    No Known Activations