© 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. 63826
    Prev
    Next
    INDEX
    Explanations

    based on, about, defined by

    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
    hee
    -0.08
    å·¥ä½ľä¸ĬçļĦ
    -0.08
    ujud
    -0.08
    ewa
    -0.07
    æĨ¬
    -0.07
    guas
    -0.07
    çī¹åĪ«
    -0.07
    ĩ´
    -0.07
    anium
    -0.07
    olari
    -0.07
    POSITIVE LOGITS
    ä¸įåľ¨äºİ
    0.11
     solely
    0.09
    èĢĮåľ¨äºİ
    0.08
     semata
    0.08
     primarily
    0.08
    çļĦä¸įæĺ¯
    0.08
    ãģĤãģı
    0.07
    åľ¨äºİ
    0.07
     either
    0.07
     instead
    0.07
    Activations Density 0.141%

    No Known Activations