© 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. 54958
    Prev
    Next
    INDEX
    Explanations

    decomposition and classification

    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
     inadvert
    -0.08
    è··
    -0.08
     espec
    -0.08
    æİ¥ä¸ĭ
    -0.07
    getragen
    -0.07
    渺
    -0.07
    çIJª
    -0.07
    æķĪæĩī
    -0.07
    prox
    -0.07
    pling
    -0.07
    POSITIVE LOGITS
     decomposition
    0.10
     Decom
    0.09
     decom
    0.08
    åĪĨ解
    0.08
     unique
    0.07
     uniqueness
    0.07
    å®ļçIJĨ
    0.07
     exhaustive
    0.07
    ä¸įå®ĮçļĦ
    0.07
     theorem
    0.07
    Activations Density 0.010%

    No Known Activations