© 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. 26296
    Prev
    Next
    INDEX
    Explanations

    tube development

    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
    ä¸įå¼ĥ
    -0.08
    xies
    -0.08
    ckt
    -0.08
    èıĩ
    -0.08
    ington
    -0.07
    iken
    -0.07
    urm
    -0.07
    à¹Ģà¸ģลà¹īา
    -0.07
    家éĩĮ人
    -0.07
    uger
    -0.07
    POSITIVE LOGITS
    奢ä¾Ī
    0.08
    -rich
    0.08
    iloc
    0.07
    å¯ĮåIJ«
    0.07
    大èĢĮ
    0.07
    RTL
    0.07
    大çļĦ
    0.07
     Days
    0.07
     filling
    0.07
     richness
    0.06
    Activations Density 0.008%

    No Known Activations