© 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. 39601
    Prev
    Next
    INDEX
    Explanations

    how things behave or respond

    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
    Ĺı
    -0.10
    /from
    -0.10
    ание
    -0.10
    ámos
    -0.10
    usada
    -0.09
    -0.09
    RARY
    -0.09
    zinho
    -0.08
    gency
    -0.08
    gota
    -0.08
    POSITIVE LOGITS
    ivate
    0.10
    ÑģÑı
    0.08
    ively
    0.07
    nya
    0.07
    ings
    0.07
    ments
    0.07
    ingle
    0.06
    çļĦ
    0.06
     differently
    0.06
    /respond
    0.06
    Activations Density 0.050%

    No Known Activations