© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46536
    Prev
    Next
    INDEX
    Explanations

    mathematical group properties and exponents

    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
    PARSE
    -0.08
    ansch
    -0.08
    educt
    -0.07
    ish
    -0.07
    Flow
    -0.07
    湿润
    -0.07
    æľīæĪij
    -0.06
    .rm
    -0.06
    ظ
    -0.06
    flash
    -0.06
    POSITIVE LOGITS
     periodic
    0.08
    åįĬæķ°
    0.08
    è¿ĩåįĬ
    0.08
    ä¸Ń度
    0.07
     subgroup
    0.07
    veille
    0.07
     cycles
    0.07
     Chains
    0.07
    äºĮåįģåĽĽ
    0.07
    åij¨æľŁæĢ§
    0.07
    Activations Density 0.002%

    No Known Activations