© 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. 64080
    Prev
    Next
    INDEX
    Explanations

    "is not" patterns

    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
    reh
    -0.08
    æī¾äºº
    -0.07
    ÙĪاب
    -0.07
    annis
    -0.07
    转贴
    -0.07
     manh
    -0.07
    çªĿ
    -0.07
    ãģĻãģIJ
    -0.07
    çīĽèĤ¡
    -0.07
    ))/(
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¸įåı¯èĥ½çļĦ
    0.08
    aise
    0.07
     Nol
    0.07
    åı¯ä»¥åIJĹ
    0.07
    èĭ±ä¼¦
    0.07
    _NC
    0.07
    åIJİåı°
    0.06
     Scheme
    0.06
    stile
    0.06
    ä¹ĭéĹ´çļĦçŁĽçĽ¾
    0.06
    Activations Density 0.006%

    No Known Activations