© 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. 61822
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
    åIJĦæĸ¹éĿ¢
    -0.09
    åķĨæłĩä¿¡æģ¯
    -0.09
    upd
    -0.08
    æĥħåĨµåĪĨæŀIJ
    -0.08
    archs
    -0.08
    portun
    -0.08
    åĪĽéĢłæĿ¡ä»¶
    -0.08
    ä¿ĿæĬ¤ä½ľçĶ¨
    -0.08
    kest
    -0.08
     prelim
    -0.08
    POSITIVE LOGITS
    æį¢ç®Ĺ
    0.12
    计éĩı
    0.11
     conversions
    0.11
    ä¸Īéĩı
    0.10
     units
    0.09
     Units
    0.09
     measurement
    0.09
    æµĭéĩı
    0.09
    度éĩı
    0.09
     measurements
    0.09
    Activations Density 0.043%

    No Known Activations