© 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. 18193
    Prev
    Next
    INDEX
    Explanations

    negation and contractions like isn't

    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
    æīŃ
    -0.07
    ä¸įæĥĬ
    -0.06
    essin
    -0.06
    _NS
    -0.06
    ç¡®ä¿Ŀ
    -0.06
    empor
    -0.06
    es
    -0.06
    uari
    -0.06
     min
    -0.06
    æĸ°æĺ¥
    -0.06
    POSITIVE LOGITS
    tracts
    0.08
    æĽ´ä¸įæĺ¯
    0.08
    ä¸įæĺ¯è¯´
    0.08
    ä¹ĭæĦı
    0.08
     assoluto
    0.08
    èĢĮæĺ¯
    0.08
     altogether
    0.08
    èĢĮåľ¨äºİ
    0.07
    èĢĮæĺ¯åľ¨
    0.07
    bish
    0.07
    Activations Density 0.096%

    No Known Activations