© 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. 43697
    Prev
    Next
    INDEX
    Explanations

    plant descriptions

    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
     realization
    -0.07
    stein
    -0.07
    éĢĤå½ĵçļĦ
    -0.06
    ungan
    -0.06
    abr
    -0.06
     realize
    -0.06
    CTRL
    -0.06
    è°ĥæķ´åĴĮ
    -0.06
    éĢĤå½ĵ
    -0.06
    æľīæķĪæľŁåĨħ
    -0.06
    POSITIVE LOGITS
    ciano
    0.08
    мÑģ
    0.08
    _stderr
    0.08
    знаком
    0.07
    luss
    0.07
     moderately
    0.07
    udiant
    0.07
    åħ¸åŀĭçļĦ
    0.07
    AHAN
    0.07
    herits
    0.07
    Activations Density 0.211%

    No Known Activations