© 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. 4068
    Prev
    Next
    INDEX
    Explanations

    agreement and support

    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
    mailer
    -0.08
    ä¸įè¦ģå¿ĺè®°
    -0.08
    ãģªãĤĵãģ¨
    -0.07
     supposedly
    -0.07
    好åĥıæĺ¯
    -0.07
    мей
    -0.07
    ä¸į注æĦı
    -0.07
    éĤ£ä½łå°±
    -0.07
    ä½łä¸įçŁ¥éģĵ
    -0.07
    à¹ģสà¸Ļ
    -0.07
    POSITIVE LOGITS
     personally
    0.10
     myself
    0.09
     pribadi
    0.09
    æķ¬ä½©
    0.09
     persönlich
    0.08
     strongly
    0.08
     respectfully
    0.08
    æĭĿ
    0.08
     unequiv
    0.08
     лиÑĩно
    0.08
    Activations Density 0.758%

    No Known Activations