© 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. 31911
    Prev
    Next
    INDEX
    Explanations

    mathematics and science topics

    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
    åĢĻ
    -0.07
    çļĭ
    -0.07
    æĦĪ
    -0.06
    侯
    -0.06
     Pes
    -0.06
    å¥İ
    -0.06
    å¹Į
    -0.06
    icine
    -0.06
    æľ¬äºº
    -0.06
    ç¼ĸèĢħ
    -0.06
    POSITIVE LOGITS
    åį³
    0.15
    ä¹Łå°±æĺ¯
    0.14
    åį³åľ¨
    0.11
    åį³ä¸º
    0.11
    æĪĸèĢħ说
    0.10
     czyli
    0.10
     ì¦ī
    0.10
    ì¦ī
    0.10
    åį³ä»¥
    0.10
    åį³çĶ¨
    0.10
    Activations Density 0.087%

    No Known Activations