© 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. 49353
    Prev
    Next
    INDEX
    Explanations

    links and formatting

    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
    天ç¥ŀ
    -0.07
    便èĥ½
    -0.07
    ovel
    -0.07
    eres
    -0.07
    ä¸ĢçĶŁ
    -0.07
    ',//
    -0.07
    èĢ½
    -0.07
    ç¦ıç¦Ħ
    -0.06
    ç»ıæµİæĮĩæłĩ
    -0.06
    çIJĨæīĢ
    -0.06
    POSITIVE LOGITS
    室åĨħå¤ĸ
    0.08
    å¤ªè¿ľ
    0.07
    驼
    0.07
     Icons
    0.07
    reater
    0.06
    ãģ¾ãģı
    0.06
    æŃ£æĸĩ
    0.06
    crest
    0.06
    æĮģç»Ńå¼Ģå±ķ
    0.06
    å¥ĩ迹
    0.06
    Activations Density 0.106%

    No Known Activations