© 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. 56067
    Prev
    Next
    INDEX
    Explanations

    demonstrate or revealed

    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
     Certa
    -0.08
    æ¯Ķåݻ年åIJĮæľŁ
    -0.08
    ergen
    -0.07
    toral
    -0.07
     jour
    -0.07
     PERT
    -0.07
     flas
    -0.07
     statewide
    -0.07
    _tC
    -0.07
    å±ħæĺĵ
    -0.07
    POSITIVE LOGITS
     Bose
    0.10
     semiclassical
    0.09
    èµ
    0.09
    ç¦ģ
    0.09
    kov
    0.09
     physicists
    0.08
    åİŁåĪĻä¸Ĭ
    0.08
     bos
    0.08
     phenomen
    0.08
    é¢Ħè¨Ģ
    0.08
    Activations Density 0.317%

    No Known Activations