© 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. 7362
    Prev
    Next
    INDEX
    Explanations

    development and related processes

    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
    uyan
    -0.08
    -containing
    -0.07
    .fromString
    -0.07
    åĮĸçī©
    -0.07
    .hom
    -0.07
    å²IJ
    -0.07
    åĪĨæł¡
    -0.07
     buatan
    -0.07
     بÙĪدÙĨ
    -0.07
    mostat
    -0.07
    POSITIVE LOGITS
    å®ŀè·µä¸Ń
    0.11
    å®ŀåĬ¡
    0.08
    ä¸ŃçļĦ
    0.08
    ä¸Ń使çĶ¨
    0.07
     practice
    0.07
    ä¸İçłĶ究
    0.07
    èĢħ们
    0.07
    å®ŀè·µ
    0.07
    ä¸Ń对
    0.07
    çĶ¨çļĦ
    0.07
    Activations Density 0.205%

    No Known Activations