© 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. 31912
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables

    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
    shiv
    -0.08
    ramework
    -0.07
    好åѦ
    -0.07
    ONGL
    -0.07
    /win
    -0.07
    HONE
    -0.07
    æĺ¥æļĸ
    -0.07
     Lục
    -0.07
    коле
    -0.07
    ä¹Ŀ寨
    -0.07
    POSITIVE LOGITS
    寸
    0.09
    代ä¹ĭ
    0.07
    mot
    0.07
    ok
    0.06
    éĢĤåºĶæĢ§
    0.06
    ç³Ĭ
    0.06
    æĭ©
    0.06
    æĦı
    0.06
    L
    0.06
    æĭ¬
    0.06
    Activations Density 0.004%

    No Known Activations