© 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. 24423
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    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
    leÅŁ
    -0.07
    gian
    -0.07
    ä»İ鼶
    -0.06
    alkan
    -0.06
    iming
    -0.06
    rop
    -0.06
    åĬ«
    -0.06
    gli
    -0.06
    ting
    -0.06
     [[[
    -0.05
    POSITIVE LOGITS
    建ä¸ļ
    0.08
    Æ¡
    0.08
    éĢļçŁ¥æĪij
    0.08
    /sdk
    0.08
    Æ°á»Ľ
    0.07
    åĸ±
    0.07
    ÙĪاÙħ
    0.07
    åŁİ举
    0.07
    pcm
    0.07
     Dinh
    0.07
    Activations Density 0.027%

    No Known Activations