© 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. 29909
    Prev
    Next
    INDEX
    Explanations

    bitwise operators and masks

    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
    adol
    -0.09
    繫
    -0.08
    åı£å¾Ħ
    -0.07
    æķ°éĩı
    -0.07
    å
    -0.07
    çļĦæķ°éĩı
    -0.07
    LABEL
    -0.07
    æ¯Ķä¾ĭ
    -0.07
    /antlr
    -0.07
    请èģĶç³»æĪij们
    -0.07
    POSITIVE LOGITS
     bitwise
    0.14
     hexadecimal
    0.09
     Bits
    0.09
     XOR
    0.08
     ë¹ĦíĬ¸
    0.08
    hex
    0.08
    bits
    0.08
     bitmask
    0.08
     proš
    0.08
     bits
    0.08
    Activations Density 0.014%

    No Known Activations