© 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. 11673
    Prev
    Next
    INDEX
    Explanations

    Dallas Mavericks

    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
    irl
    -0.07
    ATUS
    -0.07
    å¥½å¥½åľ°
    -0.07
    æ²ĥå°Ķ
    -0.07
    åŁ¹
    -0.06
     [&
    -0.06
     unread
    -0.06
    Cir
    -0.06
    Enumerator
    -0.06
    лиÑĤа
    -0.06
    POSITIVE LOGITS
    aley
    0.08
    бÑĢи
    0.07
    çļĦæ¯Ķè¾ĥ
    0.07
    ä¸įæĪIJ
    0.07
    udos
    0.07
    -License
    0.07
    igel
    0.07
    æ¯ĶåĪ«äºº
    0.07
    neze
    0.06
    åıĸå¾Ĺæĸ°
    0.06
    Activations Density 0.001%

    No Known Activations