© 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. 25041
    Prev
    Next
    INDEX
    Explanations

    year followed by location or subject

    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
    æ¯ı天éĥ½åľ¨
    -0.07
    æ¯ı天æĻļä¸Ĭ
    -0.07
    æ¯ı天éĥ½
    -0.07
    æĸĩéĿ©
    -0.06
    寡
    -0.06
    ately
    -0.06
    åĿĬ
    -0.06
     Pett
    -0.06
    æ¯ı天éĥ½æľī
    -0.06
     Sez
    -0.06
    POSITIVE LOGITS
    çīĪçļĦ
    0.09
    ewolf
    0.08
     rentrée
    0.08
    çīĪ
    0.07
     nanti
    0.07
     prossimo
    0.07
    utzer
    0.07
     edition
    0.07
    æĸ°å½¢åĬ¿ä¸ĭ
    0.07
    าà¸ĩ
    0.07
    Activations Density 0.304%

    No Known Activations