© 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. 11631
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and code 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
    amenta
    -0.08
    SEMB
    -0.08
    ONOM
    -0.07
    iard
    -0.07
    ecem
    -0.07
    ByUrl
    -0.07
     calab
    -0.07
    &D
    -0.07
    apy
    -0.07
    elat
    -0.07
    POSITIVE LOGITS
    ä¹Ŀ
    0.06
    аÑĢи
    0.06
    ude
    0.06
     prem
    0.06
     u
    0.06
    angkan
    0.06
     x
    0.06
    u
    0.06
    ä¸įåĪ°çļĦ
    0.06
    åĴĮä¿ĿæĬ¤
    0.06
    Activations Density 0.047%

    No Known Activations