© 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. 11644
    Prev
    Next
    INDEX
    Explanations

    quoted strings and punctuation

    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
    theless
    -0.08
    é¥®é£Łä¸Ĭ
    -0.08
    üns
    -0.08
    ëĶĶìĸ´
    -0.08
    seh
    -0.08
    zier
    -0.07
    ljan
    -0.07
    opil
    -0.07
    ìŀIJ격
    -0.07
     doGet
    -0.07
    POSITIVE LOGITS
    ven
    0.07
    举
    0.07
    otto
    0.07
    éĥ¨éŨ
    0.07
    æł¼å°Ķ
    0.06
    è¦ģ为
    0.06
    veni
    0.06
    èĭ¥æĹł
    0.06
    eturn
    0.06
     intelligent
    0.06
    Activations Density 0.003%

    No Known Activations