© 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. 24312
    Prev
    Next
    INDEX
    Explanations

    increase or decrease of substances

    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
    è¿ĶåĽŀ顶éĥ¨
    -0.08
    ä¸Ĭ马
    -0.08
    æĻ®æ£®
    -0.07
    пеÑĩаÑĤ
    -0.07
    åľ¨èģĮçłĶ究çĶŁ
    -0.07
    Stamped
    -0.07
    å°½æĥħçļĦ
    -0.07
    æŁ¥æĶ¶
    -0.07
     онкологи
    -0.07
    æĽ´å¤ļ精彩
    -0.07
    POSITIVE LOGITS
     assay
    0.08
     rescued
    0.07
     rescue
    0.07
    æ´»
    0.07
    é»ijæļĹä¸Ń
    0.07
    è¿ĩå¤ľ
    0.07
    ä¸į论
    0.07
    è¦ı
    0.07
     abol
    0.07
    æģ¢å¤įæŃ£å¸¸
    0.07
    Activations Density 1.496%

    No Known Activations