© 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. 28333
    Prev
    Next
    INDEX
    Explanations

    math and machine contexts

    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
    bahan
    -0.09
    oola
    -0.08
    iben
    -0.08
    angu
    -0.08
    olare
    -0.08
    igli
    -0.08
    olat
    -0.08
    ï¸İ
    -0.07
    _callbacks
    -0.07
    áž
    -0.07
    POSITIVE LOGITS
     probable
    0.07
     Machine
    0.07
     machine
    0.06
    Machine
    0.06
    人影
    0.06
     Cah
    0.06
    åģ¶
    0.06
    ior
    0.06
    ®
    0.06
    ah
    0.06
    Activations Density 0.001%

    No Known Activations