© 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. 8370
    Prev
    Next
    INDEX
    Explanations

    code snippets or symbols

    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
    ×ķ×¢
    -0.07
    æĹłå¿ĥ
    -0.07
    æĸĩåĵ²
    -0.07
    bek
    -0.07
    aign
    -0.07
     DONE
    -0.06
    noinspection
    -0.06
    ertz
    -0.06
    æĩĤ
    -0.06
     pequ
    -0.06
    POSITIVE LOGITS
    ä¸Ģå®ļéĩıçļĦ
    0.08
    大峡谷
    0.07
    éĢĤéĩıçļĦ
    0.07
    partis
    0.07
    åįģç«ł
    0.07
    éĢĤéĩı
    0.07
    åıĤèĢĥä»·æł¼
    0.07
    acial
    0.07
    _environment
    0.06
    大éĩı
    0.06
    Activations Density 0.002%

    No Known Activations