© 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. 12213
    Prev
    Next
    INDEX
    Explanations

    storage and buffering

    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
    ä»İ严
    -0.07
    ä¸īè§Ĥ
    -0.07
    bane
    -0.07
    骨èĤī
    -0.07
    å´Ĺ
    -0.07
    åĬĪ
    -0.06
    æĴķ
    -0.06
    ãĤĴåĩºãģĻ
    -0.06
    achim
    -0.06
    ilog
    -0.06
    POSITIVE LOGITS
     storing
    0.22
    åŃĺåĤ¨
    0.22
     storage
    0.22
    åĤ¨åŃĺ
    0.21
    è´®åŃĺ
    0.19
     Storage
    0.18
    storage
    0.18
     ÑħÑĢанениÑı
    0.18
    貯
    0.17
    åĤ¨
    0.17
    Activations Density 0.376%

    No Known Activations