© 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. 7528
    Prev
    Next
    INDEX
    Explanations

    maybe, perhaps, might

    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
    icone
    -0.08
    onnen
    -0.08
    ecas
    -0.07
    chwitz
    -0.07
    ảo
    -0.07
    ÅĤaszc
    -0.07
    Allem
    -0.07
    çĥŃéŨæĸĩç«ł
    -0.07
    arget
    -0.07
    asin
    -0.07
    POSITIVE LOGITS
     maybe
    0.09
     perhaps
    0.09
     instead
    0.08
    ä¹Łè®¸
    0.08
     vielleicht
    0.07
     might
    0.07
    prest
    0.07
     Maybe
    0.07
    æĪĸ许
    0.07
    ä¸įæĮī
    0.07
    Activations Density 0.006%

    No Known Activations