© 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. 24592
    Prev
    Next
    INDEX
    Explanations

    German cities

    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
     lul
    -0.07
    æµıè§Ī次æķ°
    -0.07
    _workspace
    -0.07
    Plain
    -0.06
    æĩ¦
    -0.06
    ä¸ĭæīĭ
    -0.06
    éĩįçļĦ
    -0.06
    бÑĢ
    -0.06
    oland
    -0.06
     hus
    -0.06
    POSITIVE LOGITS
    åīį两
    0.10
    åīįä¸ī
    0.10
    åīį两天
    0.08
     decks
    0.07
    é¢ł
    0.07
    .before
    0.07
    éħ¸ç¢±
    0.07
    `${
    0.07
    LING
    0.07
     Dét
    0.07
    Activations Density 0.156%

    No Known Activations