© 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. 2529
    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
    lopedia
    -0.09
    ÅĪ
    -0.08
    agher
    -0.08
    并èĮĤ
    -0.08
    htable
    -0.08
    owing
    -0.08
    ért
    -0.08
    ë¦ĩ
    -0.07
    à¹ī
    -0.07
    ansion
    -0.07
    POSITIVE LOGITS
    еÑĨ
    0.07
    ize
    0.07
    en
    0.06
    ate
    0.06
    åĴĮåŃ¦ä¹ł
    0.06
    dav
    0.06
     ÑĢÑĭ
    0.06
    åĩºèĩªå·±çļĦ
    0.06
     about
    0.06
    èıħ
    0.06
    Activations Density 0.000%

    No Known Activations