© 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. 13767
    Prev
    Next
    INDEX
    Explanations

    mathematical/programming variables and assignments

    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
    ystem
    -0.08
     عاج
    -0.07
    æĪĸå¤ļ
    -0.07
    å°±æĺ¯çĶ¨
    -0.07
    大å¸Ŀ
    -0.07
    ç²¹
    -0.07
    ä½Ĩä¸įæĺ¯
    -0.06
    ideo
    -0.06
    åĴĮåīį
    -0.06
    å·¥ä½ľä¸Ĭ
    -0.06
    POSITIVE LOGITS
    çļĦèĮĥåĽ´
    0.08
    èĮĥåĽ´
    0.08
    ropp
    0.07
     gotta
    0.07
     cÃłng
    0.07
     Scoped
    0.07
     range
    0.07
    ney
    0.07
    erna
    0.07
    ä»¬åľ¨
    0.07
    Activations Density 0.011%

    No Known Activations