© 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. 24093
    Prev
    Next
    INDEX
    Explanations

    timing and freshness

    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
     resolve
    -0.07
    æ¯ıå¹´
    -0.07
    模ç³Ĭ
    -0.07
    èĸ°
    -0.07
    resolve
    -0.07
    åĪĨ辨çİĩ
    -0.07
     resolves
    -0.07
     resolution
    -0.07
    AccessType
    -0.07
     foundational
    -0.07
    POSITIVE LOGITS
     freshness
    0.11
    æľīæķĪæľŁåĨħ
    0.11
    æĸ°é²ľ
    0.10
    èĢ½æIJģ
    0.10
     transport
    0.10
    fresh
    0.10
     Transport
    0.09
    æĸ°é²ľçļĦ
    0.09
    transport
    0.09
    ä¿Ŀé²ľ
    0.09
    Activations Density 0.173%

    No Known Activations