© 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. 65155
    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
    schw
    -0.07
    æµĨ
    -0.07
    Targets
    -0.06
     rapporti
    -0.06
    æµĵ
    -0.06
    ä¹ĭæŃĮ
    -0.06
    à¨
    -0.06
    imbul
    -0.06
    AO
    -0.06
    æĹłæŶæĹłåĪ»
    -0.06
    POSITIVE LOGITS
    åŁł
    0.07
    åIJĦ个æĸ¹éĿ¢
    0.07
    afe
    0.07
    opat
    0.07
     leck
    0.07
    ä¾£
    0.07
    å°ıåĪ°
    0.06
    .priv
    0.06
    trol
    0.06
    åºĶå½ĵåIJij
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.