© 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. 20659
    Prev
    Next
    INDEX
    Explanations

    special characters or code formatting

    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
    mű
    -0.09
    bacher
    -0.08
    ally
    -0.08
    æĥħåĨµåĪĨæŀIJ
    -0.08
     thoại
    -0.08
    urada
    -0.08
    alles
    -0.08
    iglio
    -0.07
    ophile
    -0.07
    amia
    -0.07
    POSITIVE LOGITS
    ãģļãĤĮ
    0.06
    大
    0.06
     {}).
    0.06
    aji
    0.06
    ادات
    0.06
    uchs
    0.05
     rassegna
    0.05
    erez
    0.05
    Ł
    0.05
    æľº
    0.05
    Activations Density 0.015%

    No Known Activations