© 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. 17776
    Prev
    Next
    INDEX
    Explanations

    image filenames with .tif

    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
    Ñĥго
    -0.07
    å¾·å°Ķ
    -0.06
    被认为
    -0.06
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.06
    彷徨
    -0.06
    æĪIJ为ä¸Ģç§į
    -0.06
    ök
    -0.06
    ä¹Łåı¯ä»¥æĺ¯
    -0.06
    [
    -0.06
    被认为æĺ¯
    -0.06
    POSITIVE LOGITS
    èı©
    0.08
    ÙĬرÙĪ
    0.07
    illons
    0.07
    ousel
    0.07
    aan
    0.07
    asakan
    0.07
    dling
    0.07
    schild
    0.07
    RIPT
    0.07
    æ¯ı天æĹ©ä¸Ĭ
    0.07
    Activations Density 0.076%

    No Known Activations