© 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. 50937
    Prev
    Next
    INDEX
    Explanations

    spontaneous or improvised

    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
    urger
    -0.08
    ãģ°ãģĭãĤĬ
    -0.07
    æ´ĭ
    -0.07
    _HOOK
    -0.07
    ajo
    -0.07
    رÙĪج
    -0.06
    _THROW
    -0.06
    彬彬
    -0.06
    çĻ¾å·Ŀ
    -0.06
    izi
    -0.06
    POSITIVE LOGITS
    èĩªåıij
    0.15
     improvised
    0.13
    èĩªè¡Į
    0.13
     spontaneous
    0.13
     espont
    0.13
     spont
    0.12
     makeshift
    0.12
     spontaneously
    0.12
    èĩªåĪ¶
    0.12
     informal
    0.12
    Activations Density 0.587%

    No Known Activations