© 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. 60448
    Prev
    Next
    INDEX
    Explanations

    journal articles and reports

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ÙĬÙĨا
    -0.08
    梳
    -0.08
    åºŀ大çļĦ
    -0.08
    ught
    -0.07
    æµ¦æ±Ł
    -0.07
    íŤ
    -0.07
    ogie
    -0.07
     kém
    -0.07
    _servers
    -0.07
    olist
    -0.07
    POSITIVE LOGITS
    å¿«éĢŁçļĦ
    0.08
    å¿«éĢŁ
    0.08
     quickest
    0.08
    çļĦå¿«éĢŁ
    0.08
     rapides
    0.08
    ç®ĢçŁŃ
    0.08
     سرÙĬعة
    0.08
     quick
    0.08
     rápid
    0.08
     rapid
    0.07
    Activations Density 0.030%

    No Known Activations