© 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. 12568
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    sz
    -0.08
    åķ§åķ§
    -0.08
    å±±ä¹ĭ
    -0.07
    antry
    -0.07
    dej
    -0.07
    ÑģÑĮ
    -0.06
    arvi
    -0.06
     Popular
    -0.06
    Ø©
    -0.06
     ×Ĺ×Ļ
    -0.06
    POSITIVE LOGITS
    éĿĸ
    0.07
    à¸Ĺุ
    0.07
    iett
    0.07
    plementary
    0.07
    ertif
    0.07
     tenden
    0.07
    ahn
    0.07
    aptive
    0.07
    帷å¹ķ
    0.06
     Revel
    0.06
    Activations Density 0.000%

    No Known Activations