© 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. 51126
    Prev
    Next
    INDEX
    Explanations

    glycol or acid compounds

    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
    abar
    -0.08
    游åĪĥ
    -0.08
    çĦ¶å¤§
    -0.08
    æĬĢå·§åĴĮ
    -0.08
    æĽ´æĸ°èĩ³
    -0.08
    ä¹ĭåīįå°±
    -0.08
    oner
    -0.08
    à¹Ģรืà¸Ńà¸Ļ
    -0.08
    æĤīæķ°
    -0.08
    burgh
    -0.08
    POSITIVE LOGITS
    å¦ĤåĽ¾æīĢ示
    0.10
     automobile
    0.07
    çļĦä¸Ģç§į
    0.07
    æĺ¯æĪijåĽ½
    0.07
    请åIJĮåѦ们
    0.07
    æŁIJ
    0.06
     Fic
    0.06
    ìĨ¡
    0.06
    å¦ĤåĽ¾
    0.06
    æij
    0.06
    Activations Density 0.216%

    No Known Activations