© 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. 32518
    Prev
    Next
    INDEX
    Explanations

    percentage change calculation

    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
     helic
    -0.08
     predictable
    -0.08
    bdb
    -0.08
    gens
    -0.07
    诱
    -0.07
    ård
    -0.07
    绣ä¸ĢæĢĿæĥ³
    -0.07
    ä¸ŃåĽ½é©»
    -0.07
    สัà¹Īà¸ĩ
    -0.07
    untain
    -0.07
    POSITIVE LOGITS
     ratio
    0.13
    æ¯Ķçİĩ
    0.12
     percentage
    0.12
    ratio
    0.11
     Ratio
    0.11
     ratios
    0.11
    è¡¡éĩı
    0.11
     Percentage
    0.11
    计ç®Ĺåħ¬å¼ı
    0.11
    æ¯ĶåĢ¼
    0.11
    Activations Density 0.021%

    No Known Activations