© 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. 8751
    Prev
    Next
    INDEX
    Explanations

    math variables followed by equations or delimiters

    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
    zkod
    -0.07
    æľĢåĢ¼å¾Ĺ
    -0.07
    ä¸įåľ¨ä¹İ
    -0.07
    æľĢå¤ļçļĦ
    -0.07
    åIJĦåħ·
    -0.07
    /output
    -0.07
    åĨįæİ¥åĨį
    -0.07
     Nai
    -0.07
    ä»ĸèĩªå·±çļĦ
    -0.07
     presto
    -0.07
    POSITIVE LOGITS
    飦
    0.07
    æĶ¯
    0.06
    åIJĪ
    0.06
    æħķ
    0.06
    aios
    0.06
    导
    0.06
    éħį
    0.06
    æĭĽ
    0.06
    inj
    0.06
    δί
    0.06
    Activations Density 0.005%

    No Known Activations