© 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. 47042
    Prev
    Next
    INDEX
    Explanations

    find it

    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
    ddy
    -0.08
    满æĢĢ
    -0.08
    è¿ĺä¸įçŁ¥éģĵ
    -0.08
    åĿı
    -0.07
    åįĥç§ĭ
    -0.07
    oto
    -0.07
    å£ŀ
    -0.07
    æĪijçŁ¥éģĵ
    -0.07
    à¸ģรà¸ĵà¹Į
    -0.07
    æĨ§æĨ¬
    -0.07
    POSITIVE LOGITS
    ä¹IJ趣
    0.08
    çĶ¨å¤Ħ
    0.08
     возможнÑĭм
    0.07
    æľīå¿ħè¦ģ
    0.07
    åĩºè·¯
    0.07
     useful
    0.07
    ÑģÑı
    0.07
     полезен
    0.07
     صعÙĪبة
    0.07
    åįģåĪĨéĩįè¦ģ
    0.07
    Activations Density 0.241%

    No Known Activations