© 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. 27049
    Prev
    Next
    INDEX
    Explanations

    acetic acid mixtures

    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
    Associated
    -0.07
    ä¸įæ²»
    -0.06
     Associated
    -0.06
     associated
    -0.06
    åĿ
    -0.06
     té
    -0.06
    离æĪij们
    -0.06
     Loa
    -0.06
    åı¯å°±
    -0.06
    wich
    -0.06
    POSITIVE LOGITS
    æ¯Ķä¾ĭ为
    0.10
    æ··åIJĪ
    0.10
    åī²åIJĪ
    0.10
    _percent
    0.09
    æ¯Ķä¾ĭçļĦ
    0.09
    æ¯Ķä¾ĭ
    0.09
     ìĦŀ
    0.09
    à¸ľà¸ªà¸¡
    0.08
     mixture
    0.08
     ÑģмеÑģÑĮ
    0.08
    Activations Density 0.051%

    No Known Activations