© 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. 59778
    Prev
    Next
    INDEX
    Explanations

    speaking even

    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
    æ©
    -0.08
    croft
    -0.07
    åĨī
    -0.06
    æĹłåı¯
    -0.06
    èį
    -0.06
    ç²
    -0.06
    plug
    -0.06
     pis
    -0.06
    ade
    -0.06
     yak
    -0.06
    POSITIVE LOGITS
    .um
    0.08
    aton
    0.07
    kek
    0.07
    翼翼
    0.07
    EMS
    0.07
    hung
    0.07
    æĤ¨çļĦä½įç½®
    0.07
    ä¸Ģ身
    0.07
    ini
    0.07
    бÑĢ
    0.07
    Activations Density 0.981%

    No Known Activations