© 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. 3862
    Prev
    Next
    INDEX
    Explanations

    mathematical computation and inequalities

    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
    ¡°
    -0.08
    ationToken
    -0.08
    icap
    -0.07
    æĪĸ以åħ¶ä»ĸæĸ¹å¼ı
    -0.07
    epat
    -0.07
    /ns
    -0.07
    жай
    -0.07
    scp
    -0.07
    èħĬæľĪ
    -0.07
    (___
    -0.07
    POSITIVE LOGITS
    综åIJĪè¿IJçĶ¨
    0.08
     applic
    0.07
    æł¹çļĦ
    0.07
    åıĬåħ¶åºĶçĶ¨
    0.07
    åĨħå¿ĥçļĦ
    0.07
    侯
    0.07
    æ±Ĥ解
    0.07
    综åIJĪ
    0.07
     computation
    0.07
     proficient
    0.06
    Activations Density 0.001%

    No Known Activations