© 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. 40693
    Prev
    Next
    INDEX
    Explanations

    either or

    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
     synerg
    -0.07
    æĪijèĩª
    -0.07
    CALE
    -0.07
    ils
    -0.07
    andt
    -0.06
    éĴ°
    -0.06
    à®ķà¯įà®ķ
    -0.06
    ÑģоÑİз
    -0.06
    WARN
    -0.06
    ׳×Ļ×Ķ
    -0.06
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.15
     either
    0.13
    两大类
    0.13
    è¦ģä¹Īæĺ¯
    0.13
     Either
    0.12
     Ø¥Ùħا
    0.12
     entweder
    0.12
    两类
    0.12
    Either
    0.11
    两大
    0.11
    Activations Density 0.207%

    No Known Activations