© 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. 16195
    Prev
    Next
    INDEX
    Explanations

    Jefferson Live!

    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
    мÑĥÑĢ
    -0.09
    rown
    -0.08
    ana
    -0.08
    ARENT
    -0.08
    -pane
    -0.08
    ãĤīãģªãģĦ
    -0.07
    fall
    -0.07
    anyol
    -0.07
    æľīæĪij
    -0.07
    ละ
    -0.07
    POSITIVE LOGITS
    enj
    0.07
    èĮĥæĸĩç½ij
    0.07
    elj
    0.07
    elaide
    0.07
    itude
    0.07
    isikan
    0.07
    uhe
    0.07
    еÑĩ
    0.07
    el
    0.07
    0.07
    Activations Density 0.030%

    No Known Activations