© 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. 23640
    Prev
    Next
    INDEX
    Explanations

    describing properties of operations or quantities

    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
    EDIA
    -0.08
    çĶ¨å¿ĥ
    -0.08
    æĸĩæķĻ
    -0.08
    éĶµ
    -0.08
     nát
    -0.08
    umbang
    -0.08
    ä¹Įé¾Ļ
    -0.08
    éĺµé£İ
    -0.07
    åģĩ
    -0.07
     Istitu
    -0.07
    POSITIVE LOGITS
     enough
    0.09
    æŁIJç§įæĦıä¹īä¸Ĭ
    0.08
     somehow
    0.07
     notion
    0.07
     stuff
    0.07
     notions
    0.07
     "
    0.07
     behavior
    0.06
     explo
    0.06
    оÑĢи
    0.06
    Activations Density 0.038%

    No Known Activations