© 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. 21817
    Prev
    Next
    INDEX
    Explanations

    number sequences and progressions

    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
    ç«£
    -0.09
    综åIJĪåĪĨæŀIJ
    -0.07
    tein
    -0.07
    ÑĢиан
    -0.07
    ä¸ĩ象
    -0.07
    å¹³åĿĩæ°´å¹³
    -0.07
    ä¸īåħ¬
    -0.07
    ellino
    -0.07
    andu
    -0.07
    æ¢ĵ
    -0.07
    POSITIVE LOGITS
    ä¾Ŀ次为
    0.11
     numbers
    0.09
     progression
    0.09
    ä¾Ŀ次
    0.09
    åºıåĪĹ
    0.09
     list
    0.08
     series
    0.08
     Numbers
    0.08
     sequence
    0.08
    åĪĹ表
    0.08
    Activations Density 0.013%

    No Known Activations