© 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. 51104
    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
    ±
    -0.06
    azzi
    -0.06
    /
    -0.06
    -0.06
    ä¸ĢåIJij
    -0.06
     anyhow
    -0.06
    ury
    -0.05
    ä¸ĢæĹģçļĦ
    -0.05
    ãĥĭãĤ¢
    -0.05
    uel
    -0.05
    POSITIVE LOGITS
    ĥģ
    0.08
    кÑĥлÑĮ
    0.08
     betul
    0.08
    éľĢè¦ģåIJĮ
    0.08
    avanaugh
    0.08
    ÑħÑĤа
    0.08
     ÙĨس
    0.08
    adona
    0.08
    mdl
    0.08
    æĸ°ä¹¦æݨèįIJ
    0.08
    Activations Density 0.000%

    No Known Activations