© 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. 62761
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives

    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
    æĽ´å¥½çļĦ
    -0.08
    æĽ´å¤§
    -0.08
    æĽ´å¹¿
    -0.08
    æĽ´æĸ¹ä¾¿
    -0.07
    æĽ´å¤§çļĦ
    -0.07
    æĽ´å¥½
    -0.07
    æĽ´éĩįè¦ģçļĦ
    -0.07
    .px
    -0.07
    æĽ´ä½³
    -0.07
    abe
    -0.07
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.11
    åĴĮæľĢ
    0.10
    æľĢä¸į
    0.10
     hardest
    0.10
     least
    0.10
    akest
    0.09
    ä¹Łæĺ¯æľĢ
    0.09
    Least
    0.09
    æľĢå°ij
    0.09
     among
    0.08
    Activations Density 0.093%

    No Known Activations