© 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. 23906
    Prev
    Next
    INDEX
    Explanations

    required or obligatory specific conditions

    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
    inte
    -0.08
    nicz
    -0.08
    å¿»
    -0.07
    Õ¡Õ°
    -0.07
    åt
    -0.07
    é¼ĵåĬ±ä»ĸ们
    -0.07
    orning
    -0.07
     Vitt
    -0.07
    /games
    -0.07
    Ùĩداء
    -0.07
    POSITIVE LOGITS
    æĢ§çļĦ
    0.09
    ä¸įåı¯æ¬ł
    0.09
    ãģĹãĤĤ
    0.09
    ìĤ¬íķŃ
    0.08
    æĢ§å¼º
    0.08
    жиÑĤ
    0.08
    ç»ĦæĪIJéĥ¨åĪĨ
    0.08
    æĢ§ä¸İ
    0.07
    ä¸Ķæľī
    0.07
    wajib
    0.07
    Activations Density 0.079%

    No Known Activations