© 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. 12242
    Prev
    Next
    INDEX
    Explanations

    spending money

    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
    ÑĮÑĤеÑģÑĮ
    -0.09
    erweise
    -0.07
     Sized
    -0.07
    éļĪ
    -0.07
    ijIJ
    -0.07
    umbo
    -0.07
    lene
    -0.07
     svolgimento
    -0.07
    schen
    -0.07
    беÑĢа
    -0.07
    POSITIVE LOGITS
    iture
    0.08
    amin
    0.08
    åºģ
    0.08
    å·¨èµĦ
    0.08
    elman
    0.08
    èĻij
    0.08
    itures
    0.07
    wise
    0.07
     on
    0.07
     spree
    0.07
    Activations Density 0.035%

    No Known Activations