© 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. 10187
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and tables

    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
    bane
    -0.09
    -",
    -0.08
    encontre
    -0.08
    éĩijé¾Ļ
    -0.08
    erox
    -0.08
    æĪĺ车
    -0.08
    hdl
    -0.08
    crimin
    -0.08
    eam
    -0.08
    ç´¢æĢ§
    -0.08
    POSITIVE LOGITS
    line
    0.06
    ä»°
    0.06
    пон
    0.06
    kes
    0.06
     ↵
    0.06
    çijŁ
    0.06
    çļĦä¸Ģå¹´éĩĮ
    0.06
    imports
    0.06
     cy
    0.06
    _references
    0.06
    Activations Density 0.001%

    No Known Activations