© 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. 47349
    Prev
    Next
    INDEX
    Explanations

    following Hive code

    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
     onChanged
    -0.08
    -cols
    -0.08
    ure
    -0.07
    _texts
    -0.07
    arité
    -0.07
    aint
    -0.07
     esac
    -0.07
    MMC
    -0.07
    æīĢåľ¨åŁİå¸Ĥ
    -0.07
    à¸Ĥวัà¸į
    -0.07
    POSITIVE LOGITS
    æľĢåħ³éĶ®
    0.10
    ç«Ł
    0.09
    ç«ŁçĦ¶
    0.09
    ä¹ŁéĿŀ常
    0.08
     Cruc
    0.08
    æĽ´éĩįè¦ģçļĦæĺ¯
    0.08
    ç«ŁçĦ¶æĺ¯
    0.08
     specifically
    0.08
    æľĢéĩįè¦ģçļĦæĺ¯
    0.07
    æľĢ主è¦ģ
    0.07
    Activations Density 0.390%

    No Known Activations