© 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. 49281
    Prev
    Next
    INDEX
    Explanations

    metal oxides

    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
    Margins
    -0.08
    æīĭèĦļ
    -0.07
    åĽ°æī°
    -0.07
    efa
    -0.07
    ä»ĸ身ä¸Ĭ
    -0.06
    µľ
    -0.06
    溪éķĩ
    -0.06
     sela
    -0.06
    ämt
    -0.06
    tml
    -0.06
    POSITIVE LOGITS
    ä¼Ĭæĸ¯
    0.08
    unÄĥ
    0.07
    _abort
    0.07
    å¹´æ¯ķä¸ļäºİ
    0.07
    köd
    0.07
    ?}",
    0.07
    ughter
    0.07
    afka
    0.07
    ä¸¤åĽ½
    0.07
    请åijĬçŁ¥
    0.07
    Activations Density 0.019%

    No Known Activations