© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7018
    Prev
    Next
    INDEX
    Explanations

    testing and validation sets

    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
    Negative Logits
    _inside
    -0.07
    urrenc
    -0.07
    intens
    -0.06
     thermal
    -0.06
    alten
    -0.06
    alh
    -0.06
     vertical
    -0.06
    xFFFFFF
    -0.06
    xc
    -0.06
    ../../../../
    -0.06
    POSITIVE LOGITS
     unseen
    0.09
    /validation
    0.09
    -testing
    0.09
    ,test
    0.08
    æµĭè¯ķ
    0.08
    test
    0.08
    -test
    0.08
     TESTING
    0.08
    :test
    0.08
    è¯ķéªĮ
    0.08
    Activations Density 0.031%

    No Known Activations