© 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. 29574
    Prev
    Next
    INDEX
    Explanations

    non-English 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
     jur
    -0.06
    æѦ
    -0.06
    ãĢĮ
    -0.06
    дÑĢ
    -0.06
     attributable
    -0.06
    æĬĬä»ĸçļĦ
    -0.06
    inger
    -0.06
    èĥĨæĢ¯
    -0.06
     j
    -0.06
    дÑĢе
    -0.06
    POSITIVE LOGITS
    ourd
    0.08
    éļħ
    0.07
    yme
    0.07
    éľ²å¤´
    0.07
    ë¶Ģë¡ľ
    0.07
     odm
    0.07
    èĢĮæĺ¯ä¸Ģç§į
    0.07
    جÙĪ
    0.07
    便è¦ģ
    0.07
    两å¸Ĥ
    0.07
    Activations Density 0.012%

    No Known Activations