© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59786
    Prev
    Next
    INDEX
    Explanations

    group theory elements

    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
    Negative Logits
    å´©å¡Į
    -0.07
    åĪĨç«Ļ
    -0.07
    еÑĩ
    -0.07
    çĻ¾è®¡
    -0.07
    conte
    -0.07
     вмеÑģÑĤ
    -0.07
     didirikan
    -0.07
    ARGET
    -0.07
     booming
    -0.06
    çĻ¾å®¶
    -0.06
    POSITIVE LOGITS
    个人è¡Į为
    0.08
    个人
    0.08
     본ìĿ¸ìĿĺ
    0.08
    omorphic
    0.07
    gade
    0.07
    个ä½ĵçļĦ
    0.07
    个人æĪĸ
    0.07
     bundles
    0.07
     personally
    0.07
    个人çļĦ
    0.07
    Activations Density 0.038%

    No Known Activations