© 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. 28720
    Prev
    Next
    INDEX
    Explanations

    emergence of or as

    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
    champ
    -0.09
    åijĺçļĦ
    -0.09
    ï¸ı
    -0.07
    ioneer
    -0.07
    ying
    -0.07
    ordova
    -0.07
     vendo
    -0.07
     hinweg
    -0.07
    ernen
    -0.07
    İ
    -0.07
    POSITIVE LOGITS
     victorious
    0.09
    аÑĢа
    0.09
    uest
    0.09
    antly
    0.08
    FromFile
    0.08
    новение
    0.08
    端åĢª
    0.08
    uelle
    0.07
     tarde
    0.07
    ÑĢани
    0.07
    Activations Density 0.042%

    No Known Activations