© 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. 17381
    Prev
    Next
    INDEX
    Explanations

    technical acronyms and abbreviations

    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
    asti
    -0.08
    ival
    -0.08
    enciales
    -0.07
    ibble
    -0.07
     topo
    -0.07
    ennie
    -0.07
    ariam
    -0.07
    aida
    -0.07
    ariant
    -0.07
    erven
    -0.07
    POSITIVE LOGITS
     itself
    0.12
    æľ¬èº«
    0.10
     themselves
    0.10
     stesso
    0.09
    æľ¬äººåľ¨
    0.09
    æľ¬èº«çļĦ
    0.09
     stessi
    0.09
     himself
    0.08
    æľ¬äºº
    0.08
    æľ¬èº«å°±
    0.08
    Activations Density 0.584%

    No Known Activations