© 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. 9334
    Prev
    Next
    INDEX
    Explanations

    disclaimer below

    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
     âĤ¬*
    -0.07
    itier
    -0.07
     ingy
    -0.07
    /*@
    -0.07
    ç¥Ńæī«
    -0.07
    á»ijm
    -0.07
     chÃŃ
    -0.06
    egah
    -0.06
     spect
    -0.06
    uréat
    -0.06
    POSITIVE LOGITS
     below
    0.09
     ниже
    0.08
    ä¸ĭéĿ¢
    0.08
    below
    0.08
    ç¨Ģ
    0.07
    æİ¥ä¸ĭæĿ¥çļĦ
    0.07
    лÑıн
    0.07
    ä¸ĭæĸĩ
    0.07
    à¸ķà¹Īà¸Ńà¹Ħà¸Ľ
    0.07
     next
    0.07
    Activations Density 0.154%

    No Known Activations