© 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. 20163
    Prev
    Next
    INDEX
    Explanations

    created by or authored by

    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
    entine
    -0.09
    ingly
    -0.08
     Turqu
    -0.08
    使èĩªå·±çļĦ
    -0.08
    æ¯ıåħ¬æĸ¤
    -0.08
    ä¸įæĮī
    -0.07
    åĽ¾ä¹¦ä¸ĵèIJ¥åºĹ
    -0.07
    batas
    -0.07
    游æĪıä¸ĭè½½
    -0.07
    åĪ°èĩªå·±çļĦ
    -0.07
    POSITIVE LOGITS
     autoria
    0.10
    çĶ¨å¿ĥ
    0.08
    èĢĮæĪIJ
    0.08
    并çĶ±
    0.07
     authored
    0.07
    ç½²åIJį
    0.07
    åĩºåĵģ
    0.07
     anonymous
    0.07
    åĩºèĩª
    0.07
     painstaking
    0.07
    Activations Density 0.846%

    No Known Activations