© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34799
    Prev
    Next
    INDEX
    Explanations

    my/your business logic

    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
    缸åħ³èµĦ讯
    -0.07
    ãĥ¼ãĥĦ
    -0.07
    åı½
    -0.07
    TERM
    -0.07
    apura
    -0.06
     Eck
    -0.06
    å¿ĥçĶĺæĥħæĦ¿
    -0.06
     Morton
    -0.06
    erek
    -0.06
    amah
    -0.06
    POSITIVE LOGITS
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    0.07
    ´
    0.07
     تدخÙĦ
    0.07
    æ±IJ
    0.07
    人åijĺåIJįåįķ
    0.07
    ä¸įä»ħå¦ĤæѤ
    0.07
    èįŀ
    0.07
    ½
    0.06
    ä½ľåĵģä¸Ń
    0.06
    ÙĨÙĩا
    0.06
    Activations Density 0.004%

    No Known Activations