© 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. 58316
    Prev
    Next
    INDEX
    Explanations

    counts and views

    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
    尼奥
    -0.07
    าà¸ĩ
    -0.07
    oop
    -0.06
    æ³Ľ
    -0.06
    ä¹ĭçĪ¶
    -0.06
    å¼Ĭ
    -0.06
     inclusion
    -0.06
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.06
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
    fts
    0.08
    æµıè§Īéĩı
    0.07
    atha
    0.07
    ĵ¨
    0.07
    -flex
    0.07
    printStats
    0.07
    .Physics
    0.07
    -hash
    0.07
    onal
    0.07
    .newInstance
    0.07
    Activations Density 0.003%

    No Known Activations