© 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. 24261
    Prev
    Next
    INDEX
    Explanations

    Japanese outdoor

    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
    oriously
    -0.08
    ovel
    -0.08
    ongyang
    -0.08
    áĥļáĥĿáĥij
    -0.08
    ÑĢази
    -0.08
    uffles
    -0.07
    ẵn
    -0.07
    лÑıн
    -0.07
    dae
    -0.07
    ",'
    -0.07
    POSITIVE LOGITS
    Ø©
    0.07
    ırım
    0.07
    iaux
    0.06
    ist
    0.06
    å§Ķä¼ļ
    0.06
    ation
    0.06
    er
    0.06
    yed
    0.06
    oj
    0.06
    ç½ijç«Ļé¦ĸ页
    0.06
    Activations Density 0.011%

    No Known Activations