© 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. 65360
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and code constructs

    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
     latter
    -0.08
    æĿijæĿijæ°ij
    -0.07
    åĴĮä¹īåĬ¡
    -0.07
    CDATA
    -0.07
    ipper
    -0.07
    å·¥ç¨ĭéĻ¢éĻ¢å£«
    -0.07
    spring
    -0.07
    δί
    -0.07
    .parseInt
    -0.07
    sur
    -0.06
    POSITIVE LOGITS
    çľ·æģĭ
    0.07
    oubl
    0.07
    .dk
    0.07
    züglich
    0.07
    attform
    0.07
    OLED
    0.07
    én
    0.06
    ued
    0.06
    uell
    0.06
    vole
    0.06
    Activations Density 0.002%

    No Known Activations