© 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. 23769
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

    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
    urus
    -0.09
    igator
    -0.08
    å¸ĮæľĽåı¯ä»¥
    -0.08
    _PROD
    -0.07
    gings
    -0.07
    çī¹æĸ¯
    -0.07
    Opaque
    -0.07
    åı¤å±ĭ
    -0.07
    atable
    -0.07
     nhau
    -0.07
    POSITIVE LOGITS
    által
    0.09
     otherwise
    0.08
    åIJĮæĹ¶ä¹Ł
    0.07
    ãģłãģijãģ§ãģªãģı
    0.07
     even
    0.07
    æľ¬æĿ¥å°±
    0.07
    ä¸Ģ举
    0.07
     entire
    0.07
    æľ¬å°±
    0.07
     both
    0.07
    Activations Density 0.677%

    No Known Activations