© 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. 46232
    Prev
    Next
    INDEX
    Explanations

    derived or adapted from

    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
    veni
    -0.09
    她表示
    -0.08
    缸åħ³æݨèįIJ
    -0.07
    åħ¹
    -0.07
    æ¯ıä¸Ģ个è§ĴèIJ½
    -0.07
    åĽłä¸ºä½ł
    -0.07
    ä½łè¿Ļ个
    -0.07
    究竣æĺ¯ä»Ģä¹Ī
    -0.07
     Cupertino
    -0.07
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    -0.07
    POSITIVE LOGITS
    åĩºèĩª
    0.09
    มาà¸Īาà¸ģ
    0.09
    æºIJèĩª
    0.08
    æĶ¹ç¼ĸèĩª
    0.08
    åİŁ
    0.08
     original
    0.08
    åİŁä½ľ
    0.08
     originally
    0.08
    éĢīèĩª
    0.08
     originals
    0.07
    Activations Density 0.730%

    No Known Activations