© 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. 19881
    Prev
    Next
    INDEX
    Explanations

    sports scores

    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
    enschaft
    -0.08
    enaries
    -0.07
    Vien
    -0.07
    amna
    -0.07
    åħŃä¸Ģ
    -0.07
    åĭ¤åĭī
    -0.07
     جذ
    -0.06
    %c
    -0.06
     Levin
    -0.06
     Goodman
    -0.06
    POSITIVE LOGITS
    æĤ¬æ®Ĭ
    0.08
    åĬ¿
    0.08
    åıĮæĸ¹çļĦ
    0.07
    èIJ½åIJİçļĦ
    0.07
    .match
    0.07
    ä¸Ģæĸ¹çļĦ
    0.07
    against
    0.07
    天å¤ĸ
    0.07
    åıĮæĸ¹
    0.07
     yours
    0.07
    Activations Density 0.109%

    No Known Activations