© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 63798
    Prev
    Next
    INDEX
    Explanations

    expectations, growth, awareness, coverage, features, passes, comments

    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
    UnderTest
    -0.10
    serter
    -0.09
    tright
    -0.09
    áĥIJáĥªáĥĺ
    -0.09
     Erwachs
    -0.09
     iepazīšanÄģs
    -0.09
    usercontent
    -0.09
    suming
    -0.09
    åħ¼æĢ»ç»ıçIJĨ
    -0.09
    $header
    -0.09
    POSITIVE LOGITS
    /
    0.10
    -
    0.08
     &
    0.07
    less
    0.06
     of
    0.06
    å¼Ģ
    0.06
     for
    0.06
    1
    0.06
     and
    0.06
     /
    0.06
    Activations Density 1.536%

    No Known Activations