© 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. 39611
    Prev
    Next
    INDEX
    Explanations

    case, complexity, signals, time

    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
    æĪĸ以ä¸Ĭ
    -0.07
    ãģ¿ãĤĦ
    -0.07
    lauch
    -0.07
    oten
    -0.07
    appen
    -0.07
    zio
    -0.06
    mit
    -0.06
    ibel
    -0.06
    çijŁ
    -0.06
     traumatis
    -0.06
    POSITIVE LOGITS
    ä¹Łç½¢
    0.07
    __*/
    0.07
    riter
    0.07
     ones
    0.06
    ãĤĤãģ®
    0.06
    utan
    0.06
    enheim
    0.06
    仪
    0.06
    å£Į
    0.06
    esuaian
    0.06
    Activations Density 0.185%

    No Known Activations