© 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. 38911
    Prev
    Next
    INDEX
    Explanations

    gain of function mutation

    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
    çļĦæĦıä¹ī
    -0.08
    ifa
    -0.07
    åĽĽåĪĨ
    -0.07
     rá»ī
    -0.07
    olph
    -0.07
    -Sah
    -0.07
    æ±ĩ
    -0.07
     민ê°IJ
    -0.07
    é»Ħç´ł
    -0.07
    稳å®ļæĢ§åĴĮ
    -0.07
    POSITIVE LOGITS
    æļĤæŶ
    0.08
    æľīä½Ļ
    0.08
    æĺĤ
    0.08
    å¨Ĩ
    0.07
    æľĿæ°Ķ
    0.07
     temporarily
    0.07
    天ä¹ĭ
    0.07
    åī
    0.07
    kas
    0.07
    æŃ£æ°Ķ
    0.07
    Activations Density 0.001%

    No Known Activations