© 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. 16416
    Prev
    Next
    INDEX
    Explanations

    scientific accuracy

    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
    abyrin
    -0.08
    ERRU
    -0.08
    ±
    -0.08
    ÑģкÑĥÑģ
    -0.08
    éĶ¦æ¶Ľ
    -0.07
    indsight
    -0.07
    ÑģÑı
    -0.07
    uskan
    -0.07
    åĶı
    -0.07
    شب
    -0.07
    POSITIVE LOGITS
    ÙħÙĨد
    0.08
    ifice
    0.08
    -minded
    0.08
    çķĮçļĦ
    0.08
    fully
    0.07
    yam
    0.07
    (sh
    0.07
    atorium
    0.07
    /engine
    0.07
    ĸ
    0.07
    Activations Density 0.050%

    No Known Activations