© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14917
    Prev
    Next
    INDEX
    Explanations

    testing and validation

    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
    ç§įç±»ç¹ģå¤ļ
    -0.08
     undes
    -0.07
     ticking
    -0.06
    ors
    -0.06
    ity
    -0.06
    ä¸Ģåĵģ
    -0.06
    æĪĸå¤ļæĪĸå°ij
    -0.06
    æį¢ä¸Ģ个
    -0.06
    possibly
    -0.06
    è¿Ļæł·çļĦ人
    -0.06
    POSITIVE LOGITS
    oucher
    0.09
     tentative
    0.08
    æĮīè§Ħå®ļ
    0.08
    ipple
    0.07
    _mgr
    0.07
    assen
    0.07
    issi
    0.07
    ãĥªãĥ¼ãĤ¹
    0.07
    ηÏĥη
    0.07
    TRIES
    0.07
    Activations Density 0.003%

    No Known Activations