© 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. 49857
    Prev
    Next
    INDEX
    Explanations

    first-principles calculations

    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
     variable
    -0.07
    æĬ½æł·
    -0.07
    ackets
    -0.06
     sourceMappingURL
    -0.06
    åĽºå®ļæľŁéĻIJ
    -0.06
     onstage
    -0.06
     BID
    -0.06
    ä½ļåIJį
    -0.06
    åĪĿäºĮ
    -0.06
     covert
    -0.06
    POSITIVE LOGITS
    unsch
    0.08
    Comput
    0.08
     simulations
    0.08
     raÄį
    0.08
     computational
    0.08
    Computed
    0.08
    计ç®Ĺ
    0.08
    ä¸Ģåīij
    0.08
    æ¯Ĵ
    0.08
    èįī
    0.08
    Activations Density 0.063%

    No Known Activations