© 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. 12394
    Prev
    Next
    INDEX
    Explanations

    persistence

    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
    zier
    -0.10
    åħ¢åħ¢ä¸ļä¸ļ
    -0.08
    åħ¨å¿ĥåħ¨æĦı
    -0.08
    ization
    -0.08
    ized
    -0.08
    cipt
    -0.08
    ull
    -0.07
    IZED
    -0.07
    ossal
    -0.07
    ÑģлÑĸд
    -0.07
    POSITIVE LOGITS
    ä¸įæĭĶ
    0.12
    ä¸įæ¸Ŀ
    0.11
    ä¸įåıĺçļĦ
    0.11
    ently
    0.10
    åĴĮå®ĮåĸĦ
    0.10
    éĹ®é¢ĺ导åIJij
    0.10
    ä¸į移
    0.09
    ä¸įåıĺ
    0.09
    ä¸įæĶ¾
    0.08
    ä¸įæĩĪ
    0.08
    Activations Density 0.038%

    No Known Activations