© 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. 28576
    Prev
    Next
    INDEX
    Explanations

    research documents and records

    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
    igd
    -0.08
    uchy
    -0.07
    ä¹ĭå·®
    -0.07
    à¹ĥà¸Ļà¹Ĥลà¸ģ
    -0.07
    adera
    -0.07
    ä¸įä¿¡
    -0.07
    æİĤ
    -0.07
    èĬ¸èĥ½
    -0.06
    æŁIJç§į
    -0.06
    ZZ
    -0.06
    POSITIVE LOGITS
     relevant
    0.08
    levant
    0.08
    ä¼ļåĦ¿
    0.08
    为主è¦ģ
    0.07
    rika
    0.07
    为åĩĨ
    0.07
     CEL
    0.07
    ë§ĪìŀIJ
    0.07
    èİĬ
    0.07
    relevant
    0.07
    Activations Density 0.059%

    No Known Activations