© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61119
    Prev
    Next
    INDEX
    Explanations

    oil-based ingredients or components

    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
    akas
    -0.07
    érée
    -0.07
    gesetzt
    -0.07
    emuk
    -0.07
    lež
    -0.06
    osci
    -0.06
    oskop
    -0.06
    ฯ
    -0.06
    heets
    -0.06
    isée
    -0.06
    POSITIVE LOGITS
    ãĤģãģIJ
    0.07
     gotten
    0.07
    缴æİ¥æĪĸéĹ´æİ¥
    0.07
    çļĦä¸įæĺ¯
    0.07
    -based
    0.07
    ä¹Łç½¢
    0.07
    ä»İåĵªéĩĮ
    0.07
    /]
    0.07
    aoke
    0.06
    æĿijéķĩ
    0.06
    Activations Density 0.021%

    No Known Activations