© 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. 48316
    Prev
    Next
    INDEX
    Explanations

    wave oscillation modes

    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
    angani
    -0.08
    æ¯Ĥ
    -0.08
    inkan
    -0.08
     tratt
    -0.07
    为éļ¾
    -0.07
     hustle
    -0.07
    è¯ķéªĮåĮº
    -0.07
    çĴĢ
    -0.06
    enti
    -0.06
    å·®è·Ŀ
    -0.06
    POSITIVE LOGITS
     patterns
    0.09
     pattern
    0.08
     Patterns
    0.08
    åĽ¾æ¡Ī
    0.07
     wave
    0.07
    patterns
    0.07
    attern
    0.07
    波形
    0.07
    -pattern
    0.07
    ynes
    0.07
    Activations Density 0.010%

    No Known Activations