© 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. 40173
    Prev
    Next
    INDEX
    Explanations

    errors or confusion

    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
    羸åŃIJ
    -0.08
    ä¸įéĻIJ
    -0.08
    allet
    -0.07
     sier
    -0.07
    åģ¶éģĩ
    -0.06
    æĮº
    -0.06
    好æĸĩ
    -0.06
    apun
    -0.06
     Hint
    -0.06
     Freitas
    -0.06
    POSITIVE LOGITS
    elj
    0.09
     perhaps
    0.08
     funda
    0.07
    perhaps
    0.07
    ImageData
    0.07
     Merry
    0.07
     atribu
    0.07
    èĹ
    0.07
    çİĭå°ı
    0.07
    isky
    0.07
    Activations Density 0.031%

    No Known Activations