© 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. 63364
    Prev
    Next
    INDEX
    Explanations

    court cases or legal documents

    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
     RESPONS
    -0.07
    æľīç»ıéªĮ
    -0.07
    çĻ½å¤©
    -0.06
     Pang
    -0.06
    pekt
    -0.06
    æľĽåİ»
    -0.06
     Perkins
    -0.06
    轻轻ä¸Ģ
    -0.06
     lit
    -0.06
    /../
    -0.06
    POSITIVE LOGITS
    åŁŁçļĦ
    0.07
    iée
    0.07
    建åĨĽ
    0.07
    ç²¾è¯ļ
    0.07
    æľ¬æĽ¸
    0.07
    åĩºè·¯
    0.06
    åħ¨ä¹¦
    0.06
    æĻĸ
    0.06
    çĽĸä¸ĸ
    0.06
    Binder
    0.06
    Activations Density 0.070%

    No Known Activations