© 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. 46779
    Prev
    Next
    INDEX
    Explanations

    digits and tens

    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
    wagon
    -0.07
    åįķæĸ¹éĿ¢
    -0.07
     Ranked
    -0.07
    vky
    -0.07
    æĬľãģij
    -0.07
    æĤ¨çļĦè¯Ħ论
    -0.07
    اش
    -0.07
     uploads
    -0.07
    对人类
    -0.07
    alas
    -0.07
    POSITIVE LOGITS
    åķĨçļĦ
    0.08
    istar
    0.08
    çĩķåŃIJ
    0.07
    çĩķ
    0.07
    undle
    0.07
    å¸Ń
    0.07
     quotient
    0.07
    åĥıä¸Ģåıª
    0.07
     Pirates
    0.07
    igs
    0.07
    Activations Density 0.004%

    No Known Activations