© 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. 8821
    Prev
    Next
    INDEX
    Explanations

    history of literature and art

    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
    ↵
    -0.07
    -
    -0.07
    (
    -0.07
    ç®Ģåįķ
    -0.06
    æĭ¬
    -0.06
     giz
    -0.06
    -0.06
    æľīåºı
    -0.06
    z
    -0.06
     -
    -0.06
    POSITIVE LOGITS
    ä¸įä¹ı
    0.10
    ä¹Łæľīä¸įå°ij
    0.09
    æľīä¸įå°ij
    0.09
     durchaus
    0.09
    åİĭæľº
    0.09
    kout
    0.09
    è¿ĺæľīä¸įå°ij
    0.09
    æĺ¯çĽ¸å½ĵ
    0.09
    æ¯Ķå¦Ĥåľ¨
    0.09
    /lg
    0.09
    Activations Density 0.012%

    No Known Activations