© 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. 12130
    Prev
    Next
    INDEX
    Explanations

    in vivo or in vitro studies

    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
    éĻĪ代谢
    -0.08
    à¸Ĭุ
    -0.08
    ÑĪов
    -0.08
    ç²¾èı¯
    -0.08
    çªģåĩ»
    -0.08
    _ASC
    -0.08
    vÄĥ
    -0.08
     perfecte
    -0.08
    .bz
    -0.08
    estring
    -0.08
    POSITIVE LOGITS
    fe
    0.08
    akai
    0.06
    ↵↵
    0.06
    anton
    0.06
     surroundings
    0.06
    зÑı
    0.06
    ire
    0.06
     asal
    0.06
     Schiff
    0.06
     fort
    0.05
    Activations Density 1.577%

    No Known Activations