© 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. 49424
    Prev
    Next
    INDEX
    Explanations

    pl / s or kg

    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
    undu
    -0.07
    деÑĢа
    -0.06
    å°ĨæĿ¥
    -0.06
    arer
    -0.06
    ôi
    -0.06
    ãĤ¯ãĤ¹
    -0.06
    aber
    -0.06
    zil
    -0.06
    为社ä¼ļ
    -0.06
    tvr
    -0.06
    POSITIVE LOGITS
     diserta
    0.07
    éĩijæ¡¥
    0.07
    idem
    0.07
    áĥĺáĥ¢
    0.07
     ristor
    0.07
    æĻĮ
    0.07
    uva
    0.07
     Resta
    0.07
    æĮ
    0.07
    宣åijĬ
    0.07
    Activations Density 0.004%

    No Known Activations