© 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. 38771
    Prev
    Next
    INDEX
    Explanations

    constraint binding

    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
    tene
    -0.08
    umÄģ
    -0.08
    streams
    -0.07
    _streams
    -0.07
    omma
    -0.07
    PORT
    -0.07
    upe
    -0.07
    åĵĪæĭī
    -0.07
    èĢĮä¸įè§ģ
    -0.07
    stream
    -0.07
    POSITIVE LOGITS
    åIJ¦
    0.07
     crossover
    0.07
     Applic
    0.07
    applic
    0.07
     regime
    0.07
    che
    0.07
    над
    0.07
     applic
    0.07
    éĢĤçĶ¨
    0.07
    æĺ¯ä¸Ģ缴
    0.07
    Activations Density 0.009%

    No Known Activations