© 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. 3078
    Prev
    Next
    INDEX
    Explanations

    polymerization, elastomer, surname

    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
    oc
    -0.06
    nde
    -0.06
    ä¸īæĹł
    -0.06
    ie
    -0.06
     напÑĢ
    -0.06
    gc
    -0.06
    åĴĮæĻºæħ§
    -0.06
     Readonly
    -0.06
    åĬłå¼ºäºĨ
    -0.06
    _BITS
    -0.06
    POSITIVE LOGITS
    úp
    0.08
    åIJĮæł·çļĦ
    0.07
    æ°ı
    0.07
    åIJĮ樣
    0.07
    åIJĮæł·
    0.07
     similarly
    0.07
    usten
    0.07
    帮åĬ©ä»ĸ们
    0.07
    éré
    0.07
     rapidly
    0.07
    Activations Density 0.335%

    No Known Activations