© 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. 27285
    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
    stwo
    -0.08
    γε
    -0.08
    _gettime
    -0.08
    umer
    -0.08
    stab
    -0.08
    ogr
    -0.08
     [,
    -0.08
    iability
    -0.07
    FromClass
    -0.07
    iat
    -0.07
    POSITIVE LOGITS
    çIJ³å¨ľ
    0.07
    çݲçıij
    0.07
    ledon
    0.07
    пли
    0.07
     Bits
    0.07
    æİ©
    0.07
    夺
    0.06
    iÄħ
    0.06
    lod
    0.06
    жела
    0.06
    Activations Density 0.011%

    No Known Activations