© 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. 34075
    Prev
    Next
    INDEX
    Explanations

    rate, limit, max, capacity

    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
     emb
    -0.08
    æĭĽ
    -0.06
    åħ´åįİ
    -0.06
    åŃ¦å¼Ł
    -0.06
    交çļĦ
    -0.06
    ä»½å·¥ä½ľ
    -0.06
    .readString
    -0.06
    _DISK
    -0.06
     Patr
    -0.06
    æłĵå¡ŀ
    -0.06
    POSITIVE LOGITS
    æķĪçİĩ
    0.08
    -limit
    0.08
    ê»ı
    0.08
     throughput
    0.07
     rate
    0.07
    éĻIJéĩı
    0.07
    çĸ¾
    0.07
    гÑĢÑĥзка
    0.07
     <![
    0.07
    rate
    0.07
    Activations Density 0.005%

    No Known Activations