© 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. 24628
    Prev
    Next
    INDEX
    Explanations

    names preceding et al

    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
    .insertBefore
    -0.07
    umping
    -0.07
    çݰ代åĮĸ建设
    -0.07
    èĥ¶
    -0.06
    hurst
    -0.06
    ìĥģ
    -0.06
    稼
    -0.06
    ëĤĻ
    -0.06
     ÐŁÐ»Ñİ
    -0.06
    _cuda
    -0.06
    POSITIVE LOGITS
     ÎŃγι
    0.07
    SizeMode
    0.07
     CAST
    0.07
    对è¯Ŀ
    0.07
     pocket
    0.06
     agre
    0.06
     facebook
    0.06
     Carvalho
    0.06
     diá»ĩn
    0.06
    ehold
    0.06
    Activations Density 0.018%

    No Known Activations