© 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. 9718
    Prev
    Next
    INDEX
    Explanations

    numbers after special characters

    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
    ä¸Ģé¡Ĩ
    -0.07
    ä¸Ĭè¿ĩ
    -0.07
    äng
    -0.07
    ingly
    -0.07
    quete
    -0.07
    第äºĮç§į
    -0.07
    ä¸ĢåŃĹ
    -0.06
    Ùħص
    -0.06
    -IN
    -0.06
    änd
    -0.06
    POSITIVE LOGITS
    ä¸ĥä¸ĥ
    0.08
     n
    0.08
    åħŃ
    0.08
     six
    0.08
    èĭ¥å¹²
    0.07
     nô
    0.07
    n
    0.07
    åħ«
    0.07
    åħŃçĽĺ
    0.07
     acht
    0.07
    Activations Density 0.271%

    No Known Activations