© 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. 62792
    Prev
    Next
    INDEX
    Explanations

    physical constants (g, G, c)

    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
    upp
    -0.07
    áĥłáĥĿ
    -0.06
    ä»ĺåĩº
    -0.06
    åĪ©çĽĬçļĦ
    -0.06
    orp
    -0.06
    æij
    -0.06
    æĢ§
    -0.06
    ä»ĺåĩºçļĦ
    -0.06
    çī¹æľī
    -0.06
    uplic
    -0.05
    POSITIVE LOGITS
    ê°Ĵ
    0.09
    åĢ¼åĴĮ
    0.08
    åĢ¼
    0.08
    åĢ¼æĺ¯
    0.08
    /--
    0.08
    umus
    0.08
    0.08
    ató
    0.08
    astle
    0.08
    /#
    0.07
    Activations Density 0.057%

    No Known Activations