© 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. 46952
    Prev
    Next
    INDEX
    Explanations

    variable declarations and identifiers

    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
    дÑİ
    -0.07
    áºŃm
    -0.07
    ạn
    -0.07
    raw
    -0.07
     mirac
    -0.07
    GENCY
    -0.07
    纶
    -0.07
    æĸ°æľº
    -0.07
    rompt
    -0.07
    -inner
    -0.07
    POSITIVE LOGITS
     compter
    0.07
    ertas
    0.07
    审åĪ¤
    0.07
    æĪijæĽ´
    0.06
    hap
    0.06
     !(
    0.06
     germ
    0.06
    лÑĮка
    0.06
    形象åĴĮ
    0.06
    uno
    0.06
    Activations Density 0.001%

    No Known Activations