© 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. 17972
    Prev
    Next
    INDEX
    Explanations

    comparisons of quantities

    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
    uka
    -0.07
    ubin
    -0.07
    ol
    -0.07
    uba
    -0.06
    ç«¥
    -0.06
    ult
    -0.06
    uke
    -0.06
    alc
    -0.06
    æĸĻçIJĨ
    -0.06
    ÙģÙĦ
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķçļĦ
    0.11
    ä»»ä½ķåħ¶ä»ĸ
    0.10
    ä¸ĢåĪĩçļĦ
    0.09
    以任ä½ķ
    0.09
    edly
    0.09
     بÙĥØ«ÙĬر
    0.08
    ä»»ä½ķæŶåĢĻ
    0.08
    ç½ij讯
    0.08
    ãģĿãģĨãģ§
    0.08
    izr
    0.08
    Activations Density 0.030%

    No Known Activations