© 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. 20149
    Prev
    Next
    INDEX
    Explanations

    digits and bases

    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
    ä¹ħèĢĮ
    -0.08
    atically
    -0.07
    å®ŀå®ŀåľ¨
    -0.07
    åIJĪåIJĮ约å®ļçļĦ
    -0.07
    å°¼äºļ
    -0.07
    å°¼äºŀ
    -0.07
    aus
    -0.07
    aire
    -0.07
    æ³Ľèµ·
    -0.07
    oir
    -0.07
    POSITIVE LOGITS
    erras
    0.07
    USH
    0.06
    åºĶå½ĵä¾Ŀçħ§
    0.06
     hạ
    0.06
    .dep
    0.06
    สำ
    0.06
    ç»Ļä»ĸçļĦ
    0.06
    ä»İå°ı
    0.06
    asih
    0.06
    éĪ
    0.06
    Activations Density 0.057%

    No Known Activations