© 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. 1964
    Prev
    Next
    INDEX
    Explanations

    code punctuation or keywords

    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
    mag
    -0.08
    åѦä¸İ
    -0.07
    alen
    -0.07
    uo
    -0.07
    åĴĮè°ĥæķ´
    -0.07
    eke
    -0.06
    åѦçłĶ究
    -0.06
    ÏĦζ
    -0.06
    ivi
    -0.06
     ìŀĪëĬĶëį°
    -0.06
    POSITIVE LOGITS
     appunto
    0.08
    æĭĻ
    0.07
    nado
    0.07
    wap
    0.07
    inou
    0.07
     angk
    0.07
    åĮ¿åIJįçĶ¨æĪ·
    0.07
    asion
    0.07
    oze
    0.07
    rando
    0.07
    Activations Density 0.018%

    No Known Activations