© 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. 30598
    Prev
    Next
    INDEX
    Explanations

    distinct, symmetry, distinction

    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
    RK
    -0.07
    æĪĸå¤ļ
    -0.07
    è°ģçļĦ
    -0.07
    uggy
    -0.07
    ä¸ĵåľº
    -0.07
     Hicks
    -0.07
    æ½ĩæ¹ĺ
    -0.07
    inue
    -0.07
    veen
    -0.07
    flt
    -0.07
    POSITIVE LOGITS
     distinct
    0.08
    ä¸įåIJĮ
    0.08
    对称
    0.07
    çŃīæķĪ
    0.07
    distinct
    0.07
     symmetry
    0.07
    ä¸įåIJĮçļĦ
    0.07
     distinction
    0.07
     Different
    0.07
    æĶ¾çľ¼
    0.07
    Activations Density 0.001%

    No Known Activations