© 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. 938
    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
    æľīæĸ°çļĦ
    -0.08
    enaar
    -0.07
    ÚĺÙĩ
    -0.07
    ä¸ĵä¸ļæĬĢæľ¯äººåijĺ
    -0.07
    åĪ«æľī
    -0.07
    ikov
    -0.07
    æī¬æī¬
    -0.07
    ä¼ĺåĬ¿çļĦ
    -0.06
    ickle
    -0.06
    enburg
    -0.06
    POSITIVE LOGITS
    ิà¸Ķ
    0.08
    润
    0.08
    oes
    0.08
    volta
    0.07
     fore
    0.07
    oins
    0.07
    rist
    0.07
    ãģ¬
    0.07
    oin
    0.07
     Pepper
    0.07
    Activations Density 0.000%

    No Known Activations