© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44846
    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
    lew
    -0.07
    eden
    -0.07
     Wur
    -0.07
    inate
    -0.07
    ichtige
    -0.06
    åĽĽæµ·
    -0.06
    agon
    -0.06
     quals
    -0.06
     détente
    -0.06
    _thumbnail
    -0.06
    POSITIVE LOGITS
    VML
    0.08
    ÑĢаÑĨии
    0.07
    大åĮħ
    0.07
    åĽłä¸ºæĪij
    0.07
    æĹłåIJį
    0.07
    ä¼ļ为
    0.07
    PKG
    0.07
    scoped
    0.07
    ÙĪØ·
    0.07
    æľīæĪij
    0.07
    Activations Density 0.000%

    No Known Activations