© 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. 63604
    Prev
    Next
    INDEX
    Explanations

    articulate and elaborate

    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
    ican
    -0.09
    innacle
    -0.08
    deos
    -0.08
    asin
    -0.08
    èĭ±æĸĩåIJįåŃĹ
    -0.08
    âĵĴ
    -0.07
    seud
    -0.07
    eds
    -0.07
    waan
    -0.07
    å°±æĢķ
    -0.07
    POSITIVE LOGITS
    ought
    0.08
    aining
    0.08
    æ¸ħæ¥ļ
    0.08
     why
    0.07
    cause
    0.07
     gustarÃŃa
    0.07
    ä¸įä¼ij
    0.07
    ation
    0.07
    remos
    0.07
    é¢ĸ
    0.07
    Activations Density 0.012%

    No Known Activations