© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14039
    Prev
    Next
    INDEX
    Explanations

    suffix "-ive", "-ory", "-ative"

    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
    åĮĸ管çIJĨ
    -0.08
    udir
    -0.08
    ramer
    -0.08
     entière
    -0.08
    stor
    -0.08
    lify
    -0.07
    eko
    -0.07
    izada
    -0.07
    HandlerContext
    -0.07
    erval
    -0.07
    POSITIVE LOGITS
    æĢ§çļĦ
    0.11
    ive
    0.11
    ative
    0.10
    atory
    0.10
    æĢ§å¼º
    0.09
    ensive
    0.09
    /support
    0.08
    åĴĮ建设
    0.08
    æĢ§
    0.08
    itative
    0.08
    Activations Density 0.269%

    No Known Activations