© 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. 10961
    Prev
    Next
    INDEX
    Explanations

    Agoda customer / SecretKeySpec / egg whites / RO-RO vessel

    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
    ×¢×Ķ
    -0.07
    çľĭå¾Ĺ
    -0.07
     Bingo
    -0.07
    ecker
    -0.06
    gger
    -0.06
    èİİ
    -0.06
    ç²¾
    -0.06
    ,left
    -0.06
    à¸ĸม
    -0.06
    chá
    -0.06
    POSITIVE LOGITS
    æĽ´æĸ¹ä¾¿
    0.08
    relevant
    0.07
    请èģĶç³»æĪij们
    0.07
    æł¹æį®å®ŀéĻħæĥħåĨµ
    0.07
    éķ¿å¤Ħ
    0.07
    à¹īà¸Ļ
    0.07
     harap
    0.07
    çļĦæľīæķĪ
    0.07
     ÙĨار
    0.07
    reek
    0.07
    Activations Density 0.018%

    No Known Activations