© 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. 8484
    Prev
    Next
    INDEX
    Explanations

    class names or concepts

    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
    icot
    -0.07
    éľĦ
    -0.07
    天æĺŁ
    -0.07
    umpl
    -0.06
    aq
    -0.06
    aat
    -0.06
    aos
    -0.06
    åij³çļĦ
    -0.06
     Raya
    -0.06
     Brill
    -0.06
    POSITIVE LOGITS
    åĨįæİ¥
    0.08
    å¯ĵ
    0.08
    åĪº
    0.07
     Pir
    0.07
    åħ·
    0.07
     ÙĦدÙĬÙĩا
    0.07
    ARED
    0.07
    erop
    0.07
    å½ĵ她
    0.07
    éĺ²æ´ª
    0.07
    Activations Density 0.074%

    No Known Activations