© 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. 34287
    Prev
    Next
    INDEX
    Explanations

    Greenwich Village

    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
     "
    -0.07
     (
    -0.07
    ors
    -0.07
    ols
    -0.06
    -0.06
    ets
    -0.05
    eran
    -0.05
    ily
    -0.05
    ery
    -0.05
    9
    -0.05
    POSITIVE LOGITS
    leftright
    0.09
    etenz
    0.09
    agus
    0.09
    ë´
    0.09
    ä¾Ŀæ³ķ追究责任
    0.09
     kecel
    0.09
    .jquery
    0.08
    idebar
    0.08
     appunt
    0.08
    edBy
    0.08
    Activations Density 0.106%

    No Known Activations