© 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. 40102
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    äºijé£ŀ
    -0.07
    ssen
    -0.07
    å°§
    -0.06
    ä¸Ģä½ľ
    -0.06
    otti
    -0.06
    代çłģå¦Ĥä¸ĭ
    -0.06
    eshire
    -0.06
    ç¼Ń
    -0.06
    纺
    -0.06
    çĻ½æĿ¡
    -0.06
    POSITIVE LOGITS
    ]+\
    0.08
    "},"
    0.07
    ()][
    0.07
    ettel
    0.07
    elper
    0.07
    "],"
    0.07
    ãĢįãĢĮ
    0.07
    plusplus
    0.06
    .extern
    0.06
    _tpl
    0.06
    Activations Density 0.005%

    No Known Activations