© 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. 18845
    Prev
    Next
    INDEX
    Explanations

    perturbation theory

    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
    ymous
    -0.08
    ouser
    -0.08
     Murcia
    -0.07
    èµ·å±ħ
    -0.07
    DataStream
    -0.07
    à¸Ĺรà¸ĩ
    -0.07
    azzino
    -0.07
    ioned
    -0.07
    FAULT
    -0.07
    omatis
    -0.07
    POSITIVE LOGITS
    æIJŃ建
    0.08
    åĹ
    0.08
    ä¸İéĿŀ
    0.07
    çīĩçīĩ
    0.07
    æĪĸéĿŀ
    0.07
    ushima
    0.07
    å·«
    0.07
    cking
    0.07
    (patch
    0.07
    gå
    0.07
    Activations Density 0.006%

    No Known Activations