© 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. 44329
    Prev
    Next
    INDEX
    Explanations

    chemical compounds with numerical prefixes

    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
    Negative Logits
    awan
    -0.09
    ceau
    -0.07
    ç¾Į
    -0.07
    èĩªå¤§
    -0.07
    gence
    -0.07
    immen
    -0.07
    ikkert
    -0.07
    éªĹ
    -0.07
    onga
    -0.07
    apas
    -0.06
    POSITIVE LOGITS
    âĢIJ
    0.07
    çī¹èī²ç¾İé£Ł
    0.07
    ä¸Ģåľ°
    0.07
    ÙĴÙĦÙIJ
    0.07
    одно
    0.07
    çī¹æĸ¯
    0.07
    å°ıç¼ĸå°±
    0.07
    å§Ĭ妹
    0.07
    çīĪæĿĥ声æĺİ
    0.06
     mixed
    0.06
    Activations Density 0.109%

    No Known Activations