© 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. 19362
    Prev
    Next
    INDEX
    Explanations

    ãĤĴ

    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
    mente
    -0.11
    ï¸ı
    -0.10
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.09
    ly
    -0.09
    ement
    -0.08
    à¸ģาร
    -0.08
    lich
    -0.08
    ï¸İ
    -0.08
    enj
    -0.07
    ment
    -0.07
    POSITIVE LOGITS
     ë¹Ħ롯íķľ
    0.09
    ÙĴÙĨ
    0.09
    ynch
    0.08
    conde
    0.08
     ìľĦíķľ
    0.08
    à¹Ģรียà¸ļรà¹īà¸Ńยà¹ģลà¹īว
    0.08
    меÑģÑĤи
    0.08
    ierz
    0.07
    æ±Ĥæĺ¯
    0.07
    /of
    0.07
    Activations Density 0.009%

    No Known Activations