© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48692
    Prev
    Next
    INDEX
    Explanations

    dates/numbers

    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
    åħ¬åı¸èį£èªī
    -0.07
    æī¿æĭħèµ·
    -0.07
    appa
    -0.06
    ä»Ħ
    -0.06
    个人页
    -0.06
    Utc
    -0.06
    ä¸ĢæĹı
    -0.06
    iegel
    -0.06
    um
    -0.06
    âĢŀ
    -0.06
    POSITIVE LOGITS
    ç¼ĸåı·
    0.09
    åı·çļĦ
    0.09
    номеÑĢ
    0.09
    åı·åĴĮ
    0.09
    assing
    0.08
     numbering
    0.08
    ç·¨èĻŁ
    0.08
    ungsk
    0.08
    opat
    0.08
    åı·çłģ
    0.08
    Activations Density 0.073%

    No Known Activations