© 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. 27442
    Prev
    Next
    INDEX
    Explanations

    physics and math variables

    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
    æ´ĭ
    -0.07
    å¢ĥ
    -0.07
    èī
    -0.07
    ain
    -0.07
    è¶Ĭ
    -0.06
     subtract
    -0.06
    æĻ´
    -0.06
     subtraction
    -0.06
    ope
    -0.06
    å±ŀ
    -0.06
    POSITIVE LOGITS
    èĬ±ä¸Ģ
    0.08
    骼
    0.08
    .central
    0.08
    akedown
    0.08
    Scaler
    0.08
    Sizer
    0.08
     égal
    0.08
    sama
    0.08
    udir
    0.08
    WEBPACK
    0.08
    Activations Density 0.003%

    No Known Activations