© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61983
    Prev
    Next
    INDEX
    Explanations

    numbers after questions

    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
    ranges
    -0.07
    åķ¬
    -0.07
     Grip
    -0.07
    ×ķ×ķת
    -0.06
    enov
    -0.06
    æĪijå¾Īåĸľæ¬¢
    -0.06
    é¹ıé£ŀ
    -0.06
    MainThread
    -0.06
    HttpResponse
    -0.06
    æĽ²å¼ł
    -0.06
    POSITIVE LOGITS
    íĺ
    0.07
     valide
    0.07
    änd
    0.06
    _SER
    0.06
    ovice
    0.06
     ser
    0.06
    erd
    0.06
    uha
    0.06
    åħīèį£
    0.06
    è¡Ĺåı£
    0.06
    Activations Density 0.041%

    No Known Activations