© 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. 8396
    Prev
    Next
    INDEX
    Explanations

    station, thick, aired, market, seat, Engineers, piano, RSVP

    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
    нибÑĥдÑĮ
    -0.06
    éĴĪ对
    -0.06
    äº
    -0.06
    éļ
    -0.06
    å±ķå¼Ģ
    -0.06
    áĥĶáĥĹ
    -0.06
    olph
    -0.06
     Might
    -0.06
    I
    -0.06
    ä¾ĭå¦Ĥ
    -0.06
    POSITIVE LOGITS
    ä¸Ĭè¿°
    0.10
    ä¸Ĭè¨ĺ
    0.10
    ä¸ĬéĿ¢çļĦ
    0.10
     above
    0.10
    above
    0.09
    以ä¸ĬçļĦ
    0.09
    å¦Ĥä¸Ĭ
    0.09
    åľ¨ä¸ĬéĿ¢
    0.08
    以ä¸Ĭå°±æĺ¯
    0.08
     ìľĦìĿĺ
    0.08
    Activations Density 0.024%

    No Known Activations