© 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. 2695
    Prev
    Next
    INDEX
    Explanations

    power and energy measurements

    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
    ä»ĺ款æĸ¹å¼ı
    -0.08
    -definition
    -0.07
     hinweg
    -0.07
    ward
    -0.07
    精度é«ĺ
    -0.07
    endien
    -0.07
    opus
    -0.07
    äºĭæĪIJ
    -0.07
    aug
    -0.07
    ulait
    -0.07
    POSITIVE LOGITS
    agli
    0.07
     transferred
    0.06
    asse
    0.06
     distribution
    0.06
    _remaining
    0.06
    æ®ĭä½Ļ
    0.06
    Õ£
    0.06
    æľīæīĢä¸ĭéĻį
    0.06
    æĭ¢
    0.06
    lici
    0.06
    Activations Density 0.076%

    No Known Activations