© 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. 43471
    Prev
    Next
    INDEX
    Explanations

    line numbers after '+'

    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
    alink
    -0.07
    asha
    -0.07
    atlan
    -0.07
    маÑģ
    -0.07
    æĪijçŃī
    -0.07
    çļĦç¬ij声
    -0.07
    esu
    -0.07
    ymar
    -0.07
    å²Ľ
    -0.06
    åĴĮ建设
    -0.06
    POSITIVE LOGITS
    terer
    0.07
    渲
    0.07
    æĿ¯æ°´
    0.07
    rlen
    0.07
    tright
    0.07
    çīŁå°¼
    0.06
     ÑĢазве
    0.06
    oup
    0.06
    天æĺİ
    0.06
    olut
    0.06
    Activations Density 0.001%

    No Known Activations