© 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. 32857
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by names/words

    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
    ogui
    -0.09
    æł·åŃIJ
    -0.09
    latlong
    -0.09
    ÙħÙĨت
    -0.09
    å¤ĦçIJĨæĸ¹å¼ı
    -0.08
    LOPT
    -0.08
     atitude
    -0.08
     FileType
    -0.08
    æĽ´çĶŁ
    -0.08
    arque
    -0.08
    POSITIVE LOGITS
    p
    0.07
     pos
    0.06
    ze
    0.06
     coded
    0.06
     reliably
    0.06
     M
    0.06
     reel
    0.06
    äºijé£ŀ
    0.06
     brief
    0.06
    æ¦
    0.06
    Activations Density 0.001%

    No Known Activations