© 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. 16903
    Prev
    Next
    INDEX
    Explanations

    oil-in-water

    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
    inal
    -0.07
    rick
    -0.07
    左侧
    -0.07
    atina
    -0.07
    melon
    -0.07
    imb
    -0.06
    itra
    -0.06
    ièrement
    -0.06
    æĭīå°Ķ
    -0.06
    éĿłè¿ij
    -0.06
    POSITIVE LOGITS
    odate
    0.08
    ä»Ģä¹ĪçļĦ
    0.08
    odat
    0.08
    ä¸ĢåĪĩçļĦ
    0.08
    hto
    0.07
    æĪijåIJĹ
    0.07
    ndo
    0.07
    едÑĭ
    0.07
    urus
    0.07
     aina
    0.07
    Activations Density 0.181%

    No Known Activations