© 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. 22408
    Prev
    Next
    INDEX
    Explanations

    second item, phase, or aim

    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
    endio
    -0.07
    é¦ĸéĥ¨
    -0.07
    ë§ĮìĿĺ
    -0.07
    ä¸ĭåIJĮ
    -0.07
    adol
    -0.07
    abor
    -0.07
    第ä¸Ģéĥ¨
    -0.07
     ÙĤائ
    -0.07
    relude
    -0.07
    æīĢ以对
    -0.07
    POSITIVE LOGITS
    ä¹Łæĺ¯æľĢ
    0.09
     zaÅĽ
    0.09
    åĴĮæľĢ
    0.08
     же
    0.07
    åĴĮ第äºĮ
    0.07
     esetben
    0.07
    Õ
    0.07
    æĺ¯ä¸ĢäºĽ
    0.07
    ãĤĬãģ¯
    0.07
    åĪĻæĺ¯
    0.07
    Activations Density 0.024%

    No Known Activations