© 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. 50287
    Prev
    Next
    INDEX
    Explanations

    introduces a situation

    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
    åĭ¿
    -0.08
    osse
    -0.07
    à¸Ĺà¹īาย
    -0.07
     daarmee
    -0.07
     mãi
    -0.07
    stras
    -0.07
    hut
    -0.07
    ä»ħæѤ
    -0.07
    ç£Ĭ
    -0.07
    chern
    -0.07
    POSITIVE LOGITS
    éĹ®é¢ĺæĿ¥äºĨ
    0.11
     again
    0.09
     becomes
    0.09
    ä¸įåIJĮäºĨ
    0.09
    ä»Ĭ度ãģ¯
    0.08
     Again
    0.08
    Again
    0.08
    ä¸įä½ıäºĨ
    0.08
     Bec
    0.08
    éĹ®é¢ĺäºĨ
    0.08
    Activations Density 0.160%

    No Known Activations