© 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. 21435
    Prev
    Next
    INDEX
    Explanations

    additional / supplementary

    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
    绪
    -0.07
    yro
    -0.07
    çļĦå¼Ģå§ĭ
    -0.07
    æºIJ头
    -0.06
    大人çļĦ
    -0.06
    带头
    -0.06
     Leading
    -0.06
     Stand
    -0.06
    led
    -0.06
    SS
    -0.06
    POSITIVE LOGITS
     additional
    0.14
    additional
    0.14
    Additional
    0.13
     Additional
    0.13
    é¢Ŀå¤ĸ
    0.12
    .additional
    0.12
     adicionales
    0.11
     adicional
    0.11
    é¢Ŀå¤ĸçļĦ
    0.11
     supplémentaire
    0.11
    Activations Density 0.247%

    No Known Activations