© 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. 14421
    Prev
    Next
    INDEX
    Explanations

    programming and game methods

    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
    个人æĪĸ
    -0.06
    é¼»å°ĸ
    -0.06
    teca
    -0.06
     geleg
    -0.06
     foregoing
    -0.06
    ippi
    -0.06
    olog
    -0.06
    çIJĥ迷们
    -0.06
    aceut
    -0.06
    odore
    -0.06
    POSITIVE LOGITS
     accordingly
    0.09
    çĦ¶å¤§
    0.08
     enfin
    0.08
    并æıIJåĩº
    0.08
    æį®æѤ
    0.08
    æŀľçĦ¶
    0.08
     بدÙĪرÙĩ
    0.07
    è¯ĨåĪ«äºĮç»´çłģ
    0.07
    ض
    0.07
    符åIJĪè¦ģæ±Ĥ
    0.07
    Activations Density 0.010%

    No Known Activations