© 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. 63314
    Prev
    Next
    INDEX
    Explanations

    disruptor, antioxidant, promoter, stabilizer, probiotic

    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
    uz
    -0.07
    herits
    -0.07
    æłĩåĩĨè¦ģæ±Ĥ
    -0.07
    碴
    -0.07
    emean
    -0.07
    绸
    -0.07
    两å¤Ħ
    -0.07
    etem
    -0.07
    -token
    -0.07
    åIJīå°Ķ
    -0.07
    POSITIVE LOGITS
    åħ¼
    0.13
    ä½ľçĶ¨çļĦ
    0.10
    ç§įç±»ç¹ģå¤ļ
    0.09
    åħ¼å¤ĩ
    0.09
    ä½ľçĶ¨
    0.09
    çļĦä½ľçĶ¨æĺ¯
    0.09
    身åĪĨ
    0.09
    ä½ľçĶ¨æĺ¯
    0.08
    çļĦç§įç±»
    0.08
     capable
    0.08
    Activations Density 0.249%

    No Known Activations