© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2333
    Prev
    Next
    INDEX
    Explanations

    gene encodes protein

    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
    arter
    -0.07
    _PRI
    -0.07
    datal
    -0.07
    æĥĬéĻ©
    -0.07
    ستر
    -0.06
    æŃ¤èµ·å½¼ä¼ı
    -0.06
    izoph
    -0.06
    meta
    -0.06
    åīįè¿Ľ
    -0.06
    ä¹ĭ计
    -0.06
    POSITIVE LOGITS
    -functional
    0.09
    åĴĮåĬŁèĥ½
    0.09
    /function
    0.09
    èĽĭçĻ½
    0.09
     functional
    0.08
    åIJĮå·¥
    0.08
     proteins
    0.08
     coat
    0.08
    èĽĭçĻ½è´¨
    0.08
    æī§
    0.08
    Activations Density 0.249%

    No Known Activations