© 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. 44110
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific text snippets

    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
    ÑĦаÑĢ
    -0.07
    ooth
    -0.07
    umni
    -0.07
    ially
    -0.07
    æĸ¹éĿ¢ä¹Ł
    -0.07
    ä¼Ĺ人çļĦ
    -0.07
    åĨľæ°ijçļĦ
    -0.07
    oice
    -0.07
    ofil
    -0.07
    ãos
    -0.07
    POSITIVE LOGITS
    æŁIJ
    0.08
    å·²çŁ¥
    0.07
    å¦ĤåĽ¾æīĢ示
    0.06
    ytu
    0.06
    jid
    0.06
    ä¸ĭåĪĹ
    0.06
    åĪĨåĪ«
    0.06
    uben
    0.06
    義
    0.06
    .XPath
    0.06
    Activations Density 0.299%

    No Known Activations