© 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. 14376
    Prev
    Next
    INDEX
    Explanations

    accuracy, precision, and quantity

    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
    æķĪçİĩé«ĺ
    -0.08
    identes
    -0.08
    çī¹åĪ«åĸľæ¬¢
    -0.08
    kti
    -0.08
    åħĭ鼷
    -0.08
    æĹłè¾¹
    -0.08
    åĺ»
    -0.08
    mdi
    -0.08
    gra
    -0.08
    èī²åĪĹ
    -0.08
    POSITIVE LOGITS
     uncertainty
    0.10
    recision
    0.08
     uncertain
    0.08
     accuracy
    0.07
     precision
    0.07
    误差
    0.07
    精度
    0.07
    precision
    0.07
     uncertainties
    0.07
    æ°´åĩĨ
    0.07
    Activations Density 0.001%

    No Known Activations