© 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. 25223
    Prev
    Next
    INDEX
    Explanations

    concluding or contrasting transition

    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
    ÑģÑĮ
    -0.07
     shut
    -0.07
    请äºİ
    -0.07
    atici
    -0.07
    LANG
    -0.07
    -0.07
    fassung
    -0.07
    гка
    -0.06
    æľĪä¸Ń
    -0.06
    loo
    -0.06
    POSITIVE LOGITS
    opoulos
    0.07
    ä¸į误
    0.07
    éĩįæķ´
    0.07
    å¢
    0.07
    हà¥ĩ
    0.07
    çº
    0.06
    бели
    0.06
    ublin
    0.06
    æŁ
    0.06
    æĺ¾å¾ĹæĽ´åĬł
    0.06
    Activations Density 0.001%

    No Known Activations