© 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. 16795
    Prev
    Next
    INDEX
    Explanations

    providing or giving

    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
    orate
    -0.08
    okal
    -0.07
    享
    -0.07
    ier
    -0.06
    oru
    -0.06
    eso
    -0.06
    аÑĢи
    -0.06
    DESC
    -0.06
    ery
    -0.06
    .capitalize
    -0.06
    POSITIVE LOGITS
    avig
    0.09
     splitted
    0.08
    åīįåħĪ
    0.07
     thous
    0.07
    svg
    0.07
    zep
    0.07
    elet
    0.07
    лк
    0.07
     methodology
    0.07
     seper
    0.07
    Activations Density 0.001%

    No Known Activations