© 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. 9743
    Prev
    Next
    INDEX
    Explanations

    research and development verbs

    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
    举ä¸ĸ
    -0.08
    /OR
    -0.07
    νοÏį
    -0.07
    æīĢè°ĵ
    -0.07
    è¡·å¿ĥçļĦ
    -0.06
    éĽĨä¸Ńæķ´æ²»
    -0.06
    æľīæĿ¡ä»¶çļĦ
    -0.06
    ÙĥرÙĬ
    -0.06
    æĪijåij¢
    -0.06
    ä¸Ģå²ģ
    -0.06
    POSITIVE LOGITS
    度åĴĮ
    0.07
    int
    0.07
    fan
    0.07
    åĴĮ
    0.07
    ÑĨ
    0.07
     continually
    0.07
    ή
    0.07
    /
    0.06
    bin
    0.06
    ata
    0.06
    Activations Density 2.186%

    No Known Activations