© 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. 56380
    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
    çļĦåħīèį£
    -0.07
     chá
    -0.07
    prus
    -0.07
    rias
    -0.07
    plies
    -0.07
    eras
    -0.07
    \Schema
    -0.07
    IALIZ
    -0.07
    ForMember
    -0.07
    à¹Ģà¸ģล
    -0.07
    POSITIVE LOGITS
    llen
    0.07
    pum
    0.07
    osi
    0.07
     gr
    0.07
    oja
    0.07
    å±±ä¸Ń
    0.07
    ourt
    0.06
    jai
    0.06
    amis
    0.06
    allo
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.