© 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. 18176
    Prev
    Next
    INDEX
    Explanations

    accumulate or accumulation

    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
    bele
    -0.09
    isser
    -0.09
    zung
    -0.08
    iaux
    -0.08
    irim
    -0.07
    羣åģĩ
    -0.07
    hausen
    -0.07
    ä¸īæĸ¹
    -0.07
    perienced
    -0.07
    atico
    -0.07
    POSITIVE LOGITS
    积累
    0.17
    累积
    0.15
    积累çļĦ
    0.15
     accum
    0.13
     accumulation
    0.13
    ç©įãģ¿
    0.13
     accumulate
    0.13
    accum
    0.13
    累计
    0.12
     Accum
    0.12
    Activations Density 0.017%

    No Known Activations