© 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. 8338
    Prev
    Next
    INDEX
    Explanations

    volcanoes and eruptions

    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
    audi
    -0.08
     Habana
    -0.08
     поко
    -0.08
    schau
    -0.08
    veau
    -0.08
    å±Ģ
    -0.07
    å¢ŀåĢ¼
    -0.07
    .nodeType
    -0.07
    tures
    -0.07
    erso
    -0.07
    POSITIVE LOGITS
     bụi
    0.07
    åĢ¾
    0.07
    æħµ
    0.07
    ç²īå°ĺ
    0.07
     dust
    0.07
    äºĭ件
    0.07
     majeure
    0.06
    äºĭ件ä¸Ń
    0.06
    é½IJé½IJ
    0.06
     committed
    0.06
    Activations Density 0.012%

    No Known Activations