© 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. 29257
    Prev
    Next
    INDEX
    Explanations

    closing eyes or things going down

    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¶èº«
    -0.08
    áng
    -0.08
    ä¸įæĸŃå¢ŀåĬł
    -0.08
    建æĸ°
    -0.08
    anco
    -0.07
    太大äºĨ
    -0.07
    太å¤ļäºĨ
    -0.07
    åĬłå¤§äºĨ
    -0.07
    ordin
    -0.07
    åħ·æľīå¾Īé«ĺçļĦ
    -0.07
    POSITIVE LOGITS
    åĴĮè¡Į为
    0.09
    åĴĮ产åĵģ
    0.08
    ä¸ĢæŦ
    0.08
    âĢ¦).
    0.08
    åĴĮç»ıæµİ
    0.08
    ä¸Ģèĩ³
    0.08
    åĴĮèµĦæºIJ
    0.08
    èĻ½
    0.08
    è¿Ļä¸ªä¸ľè¥¿
    0.08
     _______,
    0.08
    Activations Density 0.073%

    No Known Activations