© 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. 41745
    Prev
    Next
    INDEX
    Explanations

    constraint equation

    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
    _DESCRIPTOR
    -0.08
    åĪ©çī©
    -0.08
     poop
    -0.07
    ä¸įåİĮ
    -0.07
    erecht
    -0.07
    åĸĦ
    -0.07
    ahu
    -0.07
    werking
    -0.07
    设置æľī
    -0.07
    ulet
    -0.07
    POSITIVE LOGITS
     constraint
    0.08
     rest
    0.07
    ields
    0.07
    ç´ĦæĿŁ
    0.07
    约æĿŁ
    0.07
     reform
    0.06
    reform
    0.06
    ecat
    0.06
    constraint
    0.06
     constraints
    0.06
    Activations Density 0.001%

    No Known Activations