© 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. 9573
    Prev
    Next
    INDEX
    Explanations

    matricesmatrixcaserightselectrightcase[]

    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
    ation
    -0.08
    otion
    -0.08
    ative
    -0.07
     nháºŃt
    -0.07
    UIS
    -0.07
    ullet
    -0.07
    çļĦå°ı鸣
    -0.07
    лÑij
    -0.07
    aker
    -0.07
    à¹ĥà¸Ī
    -0.07
    POSITIVE LOGITS
    ãĤĪãģĨãģª
    0.07
    ampur
    0.07
    wab
    0.07
    nda
    0.07
    ambique
    0.07
    lasse
    0.07
    bamos
    0.06
    ombat
    0.06
    ãĥ£
    0.06
    _grade
    0.06
    Activations Density 0.001%

    No Known Activations