© 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. 21377
    Prev
    Next
    INDEX
    Explanations

    differential equations and forms

    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
    shade
    -0.08
    leon
    -0.07
    ulich
    -0.07
    uesa
    -0.07
    browse
    -0.07
    usc
    -0.07
     toes
    -0.07
    殿ä¸ĭ
    -0.07
    çģ«ä¸Ĭ
    -0.07
    ajÃŃcÃŃ
    -0.07
    POSITIVE LOGITS
    æ¥Ń
    0.08
    irector
    0.07
    ä¸ļ
    0.07
    æ´ĭ
    0.07
    ä¸Ģ空
    0.06
    erp
    0.06
    çĶŁæķĪ
    0.06
    çĸ¼
    0.06
    åĽĽæĸ¹
    0.06
    ivative
    0.06
    Activations Density 0.001%

    No Known Activations