© 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. 37843
    Prev
    Next
    INDEX
    Explanations

    words ending in ative or ive

    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
    ï¸ı
    -0.11
    ingly
    -0.11
    ation
    -0.10
    ness
    -0.10
    nya
    -0.10
    ings
    -0.09
    sWith
    -0.09
    ification
    -0.09
    shire
    -0.09
    ipse
    -0.08
    POSITIVE LOGITS
     ÙĦÙĦغاÙĬØ©
    0.11
     sầu
    0.11
    /manual
    0.09
    ALLY
    0.09
    yat
    0.09
    à¥ĩ
    0.09
    olum
    0.09
    اÙģتÙĩ
    0.08
    åįģ足çļĦ
    0.08
    দà§ĩর
    0.08
    Activations Density 0.258%

    No Known Activations