© 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. 8566
    Prev
    Next
    INDEX
    Explanations

    intuitively or counterintuitively

    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
    quio
    -0.07
    ÙĥÙĨت
    -0.07
    ä¼ĹæīĢåij¨çŁ¥
    -0.07
    ä½łåij¢
    -0.07
    ä¸įåı¯æĢĿè®®
    -0.07
    eku
    -0.06
     innovación
    -0.06
    ITS
    -0.06
    身临åħ¶å¢ĥ
    -0.06
    acker
    -0.06
    POSITIVE LOGITS
    leftright
    0.09
    åľ¨äºİ
    0.08
    lessly
    0.08
    ously
    0.08
    tte
    0.08
    ingen
    0.08
    ook
    0.08
    好礼
    0.08
    عبة
    0.07
    ãĥ¼ãĥĬ
    0.07
    Activations Density 0.001%

    No Known Activations