© 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. 48328
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or code snippets

    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
    ä¸ĭè§Ĵ
    -0.06
    ixa
    -0.06
    ãģ¾ãģ¾
    -0.06
    èĮ«èĮ«
    -0.06
    geber
    -0.06
     ë°Ķíĥķìľ¼ë¡ľ
    -0.06
    å·®ä¸į
    -0.06
    xi
    -0.06
     soi
    -0.06
     Howe
    -0.06
    POSITIVE LOGITS
    ä¸ĩå²ģ
    0.08
    номеÑĢ
    0.07
     colpi
    0.07
    leden
    0.07
    天æīį
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
     ÅŁans
    0.07
     اÙĦعÙħر
    0.07
     Bertrand
    0.07
    adic
    0.07
    Activations Density 0.009%

    No Known Activations