© 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. 15476
    Prev
    Next
    INDEX
    Explanations

    financial end points

    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
    mix
    -0.08
     Dub
    -0.07
    æ¯ıä¸ĢæĿ¡
    -0.07
    mixed
    -0.07
     Mixing
    -0.07
     mixing
    -0.07
    ä¼IJ
    -0.07
    ä¾µ
    -0.06
    åĬ²
    -0.06
     dub
    -0.06
    POSITIVE LOGITS
    å±ĬæŶ
    0.10
     nanti
    0.09
    ç»ĵå±Ģ
    0.09
    à¸Ľà¸¥à¸²à¸¢à¸Ĺาà¸ĩ
    0.08
    åĪ°æŶåĢĻ
    0.08
     anticipated
    0.08
     reunion
    0.08
     пÑĢедÑĬÑı
    0.08
    ç»ĵæĿŁæŶ
    0.08
    åĪ°æŶ
    0.08
    Activations Density 0.008%

    No Known Activations