© 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. 58583
    Prev
    Next
    INDEX
    Explanations

    `that` followed by auxiliary verbs

    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
    zhou
    -0.07
     able
    -0.06
    cé
    -0.06
    à¥ĩश
    -0.06
     that
    -0.06
    criptor
    -0.06
    amm
    -0.06
    çª
    -0.06
    ApplicationContext
    -0.06
    оÑģÑĤей
    -0.06
    POSITIVE LOGITS
    ç»Ļæľĭåıĭ
    0.08
    abouts
    0.08
    å°ĶèĴĻ
    0.08
    å°ĶçļĦ
    0.07
    ×ķ
    0.07
    __;
    0.07
    Å¡n
    0.07
    ourg
    0.07
    ìķ¼
    0.07
    å°Ķ
    0.07
    Activations Density 0.011%

    No Known Activations