© 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. 29250
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èĢĮéĿŀ
    -0.09
    èĢĮä¸įæĺ¯
    -0.07
     rather
    -0.07
    丹éľŀ
    -0.07
    åĴĮæĶ¹åĸĦ
    -0.06
    eper
    -0.06
     plutôt
    -0.06
    ="[
    -0.06
     Soh
    -0.06
    oggle
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įçĶ¨
    0.10
     anymore
    0.09
    ä¸įåŃĺåľ¨
    0.09
    ä¹Łä¸įéľĢè¦ģ
    0.09
    ä¹Łä¸įå¿ħ
    0.09
    åĥı
    0.09
    ä¹Łä¸įåĨį
    0.09
    èĢĮæĺ¯
    0.08
    æĽ´æ²¡æľī
    0.08
     tampoco
    0.08
    Activations Density 0.124%

    No Known Activations