© 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. 10849
    Prev
    Next
    INDEX
    Explanations

    equations with variables

    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
    anke
    -0.07
    جرة
    -0.06
    tea
    -0.06
    ião
    -0.06
    ingen
    -0.06
    álló
    -0.06
    èľĪ
    -0.06
     Alber
    -0.06
    ICLE
    -0.06
    ayakan
    -0.06
    POSITIVE LOGITS
    egl
    0.09
    禺
    0.08
    urdy
    0.08
    人说
    0.08
    onis
    0.07
    æĽĻåħī
    0.07
    ç±³é«ĺ
    0.07
     abat
    0.07
    èĴĻå¾·
    0.07
    åĮħä½ı
    0.07
    Activations Density 0.016%

    No Known Activations