© 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. 51815
    Prev
    Next
    INDEX
    Explanations

    adding or referring to a column

    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
    _MET
    -0.07
     Constit
    -0.07
     alternativo
    -0.07
    ãĤ¯ãĥªãĥ¼
    -0.07
     alternative
    -0.06
    尼奥
    -0.06
     alternativa
    -0.06
    åİĨåı²åĴĮ
    -0.06
    ç»ıæŁ¥
    -0.06
    æľĢæĸ°èµĦ讯
    -0.06
    POSITIVE LOGITS
    éģį
    0.09
     computed
    0.08
     Values
    0.08
    ä¸Ģå¼ı
    0.08
    []=
    0.08
     запо
    0.08
    éĢIJ
    0.07
    -fill
    0.07
    åıįæĺł
    0.07
    纳æĸ¯
    0.07
    Activations Density 0.018%

    No Known Activations