© 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. 19919
    Prev
    Next
    INDEX
    Explanations

    code comments or code blocks

    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
    å°ĨæĹłæ³ķ
    -0.07
    æĿ¾
    -0.07
    boxed
    -0.06
    áĪĺ
    -0.06
    oux
    -0.06
     whatever
    -0.06
    ÏģÏīÏĥη
    -0.06
    çļĦå°±æĺ¯
    -0.06
     ders
    -0.06
    æĮ£èĦ±
    -0.06
    POSITIVE LOGITS
    adio
    0.07
    ¥
    0.07
    ç§ģèIJ¥
    0.07
    onium
    0.07
    lein
    0.07
    ToFit
    0.07
    å¹ħ
    0.07
    -awesome
    0.06
    sein
    0.06
    åĬłæĭ¿å¤§
    0.06
    Activations Density 0.003%

    No Known Activations