© 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. 50928
    Prev
    Next
    INDEX
    Explanations

    adverbs ending in -ly

    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
    sWith
    -0.11
    sto
    -0.10
    ify
    -0.09
    swith
    -0.09
    stype
    -0.09
    ÑĮÑı
    -0.09
    anes
    -0.09
    sv
    -0.09
    less
    -0.08
    ements
    -0.08
    POSITIVE LOGITS
    Ìģ
    0.12
    mph
    0.10
    Ùĭ
    0.08
    য়
    0.07
    dür
    0.07
    ÅĽÄĩ
    0.07
     parlando
    0.07
     hablando
    0.07
    ately
    0.07
    âĢ¦]
    0.07
    Activations Density 0.651%

    No Known Activations