© 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. 12735
    Prev
    Next
    INDEX
    Explanations

    .php file paths and Post objects

    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
    erÃŃa
    -0.08
    ä¹Łæľīä¸Ģå®ļçļĦ
    -0.07
    ä¸įè¿ĩæĺ¯
    -0.06
    erings
    -0.06
    ä¿
    -0.06
     Arch
    -0.06
    è°ĥçłĶåijĺ
    -0.06
     elective
    -0.06
    zap
    -0.06
    è¯Ħ课
    -0.06
    POSITIVE LOGITS
    alsy
    0.08
     uninitialized
    0.06
    æĺ¥å¤ıç§ĭåĨ¬
    0.06
    éĬ·
    0.06
    ibir
    0.06
    æĸ°æµªç½ij
    0.06
     Caucus
    0.06
     Certific
    0.06
     Successfully
    0.06
    iby
    0.06
    Activations Density 0.098%

    No Known Activations