© 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. 58438
    Prev
    Next
    INDEX
    Explanations

    special characters and separators

    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
    æĴŀä¸Ĭ
    -0.06
    ais
    -0.06
    ksi
    -0.06
    åľ¨èº«è¾¹
    -0.06
     Gem
    -0.06
     lat
    -0.06
    广åijĬ
    -0.06
    нике
    -0.06
    ople
    -0.05
    ogui
    -0.05
    POSITIVE LOGITS
    éĽĦ
    0.08
    åĭī
    0.07
    .statusText
    0.07
    å¼Ĥä½į
    0.07
    новен
    0.07
     {{--<
    0.07
    ä¸īåįģåħŃ
    0.07
    üter
    0.07
    æķ¦
    0.07
    бла
    0.07
    Activations Density 0.014%

    No Known Activations