© 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. 15775
    Prev
    Next
    INDEX
    Explanations

    cumulative total

    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
    èĽĽ
    -0.08
    æĭīæĿĨ
    -0.08
    fone
    -0.08
    è½¼
    -0.08
    ç·ł
    -0.07
    пÑı
    -0.07
    bab
    -0.07
    ä»»èģĮèµĦæł¼
    -0.07
    æĺİæĹ¥
    -0.07
    Pair
    -0.07
    POSITIVE LOGITS
    è±ģ
    0.08
     cumul
    0.08
     cumulative
    0.07
    èħ¾
    0.07
     overflow
    0.07
    Cum
    0.07
    ç´¯
    0.07
    ếp
    0.07
     total
    0.06
    累计
    0.06
    Activations Density 0.017%

    No Known Activations