© 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. 33215
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions with "let"

    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
    åħ¶å¯¹
    -0.06
    errated
    -0.06
    ÙĪرش
    -0.06
    olf
    -0.06
    ignal
    -0.06
    ister
    -0.06
    æĢİ
    -0.06
    Chapter
    -0.06
    umably
    -0.06
    ç«ĭåĪ»
    -0.06
    POSITIVE LOGITS
    oken
    0.09
    æĺ¯ä¸Ģ个éĿŀ常
    0.08
    ä½łæĺ¯ä¸Ģ个
    0.08
    æĺ¯ä¸Ģ个å¾Ī
    0.07
    æĪijæĺ¯ä¸Ģ个
    0.07
    ">',
    0.07
    æĪijæĺ¯ä¸ª
    0.07
    ehler
    0.07
    ettle
    0.07
    ä½łæĺ¯ä¸ª
    0.07
    Activations Density 0.017%

    No Known Activations