© 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. 28984
    Prev
    Next
    INDEX
    Explanations

    equation or variable assignment

    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
    åIJİæĦŁ
    -0.09
    ãģ£ãģ±ãĤĬ
    -0.08
    huis
    -0.07
    鲤鱼
    -0.07
    kiye
    -0.07
    enho
    -0.07
    éĪį
    -0.07
    èĪ¹çĶ¨
    -0.07
    >|
    -0.07
    agnost
    -0.07
    POSITIVE LOGITS
    æĸ¹ç¨ĭ
    0.09
     equations
    0.08
     equation
    0.08
    alti
    0.07
     constraint
    0.07
    约æĿŁ
    0.07
    æĸ¹ç¨ĭå¼ı
    0.07
    San
    0.07
    undler
    0.07
    ç©´
    0.07
    Activations Density 0.021%

    No Known Activations