© 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. 12284
    Prev
    Next
    INDEX
    Explanations

    automation and automated systems

    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
    nya
    -0.10
    sWith
    -0.10
    ive
    -0.10
    ings
    -0.10
    fulness
    -0.09
    ache
    -0.08
    åĴĮæľīåħ³
    -0.08
    ful
    -0.08
    æĶ¾çŁ¢
    -0.08
    angan
    -0.08
    POSITIVE LOGITS
    ç¨ĭ度
    0.12
    äºĨçļĦ
    0.11
    ç¨ĭ度çļĦ
    0.11
    ç¨ĭ度ä¸Ĭ
    0.09
    ç²ªæ±ł
    0.08
    è¶ĭåĬ¿
    0.08
    اÙģتÙĩ
    0.08
    anii
    0.08
    åľ°åİ»
    0.08
     demais
    0.08
    Activations Density 0.007%

    No Known Activations