© 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. 62970
    Prev
    Next
    INDEX
    Explanations

    proper name prefixes

    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
    人æĿ¥è¯´
    -0.06
    çĹ
    -0.06
    ä»Ģä¹Īæĺ¯
    -0.06
    sa
    -0.06
    iculty
    -0.06
    enk
    -0.06
    ibl
    -0.06
    ÃŃc
    -0.06
     alas
    -0.06
    å°ıæľ¨
    -0.06
    POSITIVE LOGITS
    &T
    0.09
    æ°ı
    0.09
    ãģ¡ãĤĥãĤĵ
    0.09
    <|box_end|>
    0.08
    ฯ
    0.08
    à¹Ģà¸Ńà¸ĩ
    0.08
    ãģ¡ãĤĥãĤĵãģ®
    0.08
    -chan
    0.08
    chado
    0.08
    's
    0.08
    Activations Density 0.117%

    No Known Activations