© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    play games and sports

    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
    äºĨä»ĸ们
    -0.09
    yled
    -0.08
    eenth
    -0.08
    å¢
    -0.08
    äºĨåľ¨
    -0.08
    ekon
    -0.08
    aufen
    -0.08
    ibas
    -0.08
    elson
    -0.08
    ário
    -0.08
    POSITIVE LOGITS
    time
    0.10
    wright
    0.09
    itional
    0.09
    fully
    0.08
    uch
    0.08
    ful
    0.08
    weise
    0.08
    seudo
    0.08
    makers
    0.07
    eworthy
    0.07
    Activations Density 0.088%

    No Known Activations