© 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. 41793
    Prev
    Next
    INDEX
    Explanations

    index j in loops or array access

    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
    é£İæ³¢
    -0.08
    jaw
    -0.07
    临
    -0.07
     aute
    -0.07
    viron
    -0.07
    Ùģا
    -0.07
    åIJĪæł¼è¯ģ
    -0.07
    QS
    -0.07
    cean
    -0.07
    imento
    -0.07
    POSITIVE LOGITS
    åŃļ
    0.07
    æĸ¯çī¹
    0.07
    HEADER
    0.07
    ardin
    0.07
    lier
    0.07
    ÑĥÑģÑĤ
    0.07
    ecute
    0.06
    é¼
    0.06
    mén
    0.06
    æ°´å¹³
    0.06
    Activations Density 0.020%

    No Known Activations