© 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. 56064
    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
    è¾»
    -0.08
    ëł¹
    -0.08
     reuni
    -0.08
    èĢĮéĻį
    -0.08
    obre
    -0.08
    ä¿Ĺ称
    -0.08
    pector
    -0.08
    .sep
    -0.08
    /format
    -0.08
    ëłĪ
    -0.07
    POSITIVE LOGITS
    对éĶĻ
    0.07
    羣åģĩ
    0.07
    arkan
    0.06
     true
    0.06
     Trang
    0.06
    est
    0.06
    aviours
    0.06
     Nun
    0.05
    ...
    0.05
     cycles
    0.05
    Activations Density 0.000%

    No Known Activations