© 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. 8098
    Prev
    Next
    INDEX
    Explanations

    either or sum

    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
    alang
    -0.08
    ikum
    -0.07
    寰
    -0.07
    æ¾ľ
    -0.07
    bergen
    -0.07
    äºĴåĬ¨
    -0.07
    ड़ा
    -0.07
     Auxiliary
    -0.07
    oten
    -0.06
    _accessor
    -0.06
    POSITIVE LOGITS
    è¦ģä¹Īæĺ¯
    0.11
    è¦ģä¹Ī
    0.11
     either
    0.10
     Either
    0.08
     либо
    0.08
    ä¹Łåı¯ä»¥æĺ¯
    0.08
    Either
    0.08
     oppure
    0.08
    eley
    0.08
    either
    0.08
    Activations Density 0.013%

    No Known Activations