© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17780
    Prev
    Next
    INDEX
    Explanations

    checked ownership assignment

    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
    obra
    -0.07
    angg
    -0.06
    åĽŃ
    -0.06
    棺
    -0.06
    åŃĺ
    -0.06
    计
    -0.06
    æ°ij
    -0.06
    æŃ¢
    -0.06
    骷
    -0.06
     ****************************************************************************
    -0.06
    POSITIVE LOGITS
    ä¸ĩåŃĹ
    0.08
    pretty
    0.08
    اعÙĬ
    0.07
    gay
    0.07
    aille
    0.07
    ÙĩÙĪد
    0.07
    हार
    0.07
    FixedSize
    0.07
     pretty
    0.07
     gaussian
    0.07
    Activations Density 0.002%

    No Known Activations