© 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. 8359
    Prev
    Next
    INDEX
    Explanations

    closing braces and code blocks

    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
    à¹Ģหล
    -0.07
    thinkable
    -0.07
    缸éļı
    -0.07
    æµ·æ³¢
    -0.06
    ä¹Į鸦
    -0.06
    holm
    -0.06
    eld
    -0.06
    ode
    -0.06
    ÙĪع
    -0.06
     блоге
    -0.06
    POSITIVE LOGITS
    aniem
    0.07
    wur
    0.07
    edImage
    0.07
    å§Ĩæĸ¯
    0.07
    å¿«çĤ¹
    0.07
     ÙĨØ´
    0.07
    .dep
    0.07
    ifax
    0.07
    اÙĨد
    0.06
    åijĬ
    0.06
    Activations Density 0.048%

    No Known Activations