© 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. 44872
    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
     roh
    -0.07
    ìŀī
    -0.07
    大åѦåŁİ
    -0.07
    à¸Ĺั
    -0.07
     Tutt
    -0.07
    åı¯æĥ³èĢĮçŁ¥
    -0.07
    anden
    -0.07
    çŀİ
    -0.07
    jos
    -0.07
    ç»Ħç»ĩå¼Ģå±ķ
    -0.07
    POSITIVE LOGITS
    æ±ŀ
    0.08
     gravitational
    0.08
     diameter
    0.07
     Schwar
    0.07
    grav
    0.07
    缴å¾Ħ
    0.07
    esium
    0.07
     Mercury
    0.07
     Fried
    0.07
     choked
    0.07
    Activations Density 0.000%

    No Known Activations