© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16241
    Prev
    Next
    INDEX
    Explanations

    chemical/synthetic reactions and processes

    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
    çIJĨ论水平
    -0.07
    代表çļĦ
    -0.07
    ä½ĵåij³
    -0.07
    oghi
    -0.07
    ümer
    -0.07
    ghost
    -0.07
    æŃ£å¸¸ä½¿çĶ¨
    -0.06
    RefCount
    -0.06
     Barber
    -0.06
    rolls
    -0.06
    POSITIVE LOGITS
    æĬĬä¸Ģ个
    0.09
    å°Ĩä¸Ģ个
    0.08
    åŀĭ
    0.08
     involving
    0.08
    ç±»åŀĭçļĦ
    0.08
    VERS
    0.07
    ç±»åŀĭ
    0.07
    æĭĨåĪĨ
    0.07
    é¡ŀåŀĭ
    0.07
    åŀĭçļĦ
    0.07
    Activations Density 0.006%

    No Known Activations