© 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. 45557
    Prev
    Next
    INDEX
    Explanations

    start of code/references

    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
    ä¸ĩäºĭ
    -0.07
    es
    -0.07
    åĪ
    -0.06
    æ²Ļæ²³
    -0.06
    fond
    -0.06
     éc
    -0.06
     Arr
    -0.06
     رس
    -0.06
    æĤĦæĤĦ
    -0.06
     bow
    -0.06
    POSITIVE LOGITS
    æĮģå¹³
    0.07
    _refer
    0.07
    inz
    0.07
    亡
    0.07
     grab
    0.07
    çī¹åĭĴ
    0.07
    æĪIJæĮĩ
    0.07
    ubl
    0.07
    åIJĮ级
    0.07
    é¢ĺåŀĭ
    0.07
    Activations Density 0.002%

    No Known Activations