© 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. 23168
    Prev
    Next
    INDEX
    Explanations

    numbers in brackets

    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
     Dres
    -0.07
    çĨł
    -0.07
    çĴŀ
    -0.07
    æĪ·åı£æľ¬
    -0.07
    quee
    -0.07
    impl
    -0.06
    梦幻
    -0.06
    æĸ°äºº
    -0.06
    ino
    -0.06
    _INF
    -0.06
    POSITIVE LOGITS
    éĴ³
    0.08
    asmine
    0.08
     overlapping
    0.07
    åį³å¢¨
    0.07
     aard
    0.07
    èĮĥåĽ´
    0.07
    æŬ
    0.07
    à¤ķà¥įषा
    0.07
    èĮĥåĽ´çļĦ
    0.07
    achine
    0.06
    Activations Density 0.015%

    No Known Activations