© 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. 55503
    Prev
    Next
    INDEX
    Explanations

    loop indices

    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
    cac
    -0.07
    æĭ¥
    -0.07
    åįĥéĩĮ
    -0.07
    éķ¿åľ¨
    -0.07
    zett
    -0.07
     thuần
    -0.07
    olit
    -0.07
    åį·
    -0.07
    çīµ
    -0.07
    sanitize
    -0.07
    POSITIVE LOGITS
    .nd
    0.08
     inclusive
    0.08
     iterating
    0.08
    ä¸ĬéĻIJ
    0.07
    Iterator
    0.07
     iterable
    0.07
     iterations
    0.07
     iterate
    0.07
    à¸Ĺรà¹Į
    0.07
     Loop
    0.06
    Activations Density 0.027%

    No Known Activations