© 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. 18825
    Prev
    Next
    INDEX
    Explanations

    control groups, saline, water, oil

    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
    roat
    -0.08
    enaar
    -0.07
    tent
    -0.07
    btc
    -0.07
    ervis
    -0.07
    ontan
    -0.07
    ameran
    -0.07
    à¸ij
    -0.07
     اÙĦجÙĦ
    -0.07
    eree
    -0.06
    POSITIVE LOGITS
    代ãĤıãĤĬãģ«
    0.08
     Protected
    0.07
    éĿ¢
    0.07
    åĩ¡
    0.07
    ä»£æĽ¿
    0.07
    Ñīе
    0.07
    ocks
    0.07
     гаÑĢанÑĤии
    0.07
    èµĦ
    0.06
    æ§ĭ
    0.06
    Activations Density 0.170%

    No Known Activations