© 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. 19911
    Prev
    Next
    INDEX
    Explanations

    questions or parenthetical clarifications

    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
    uve
    -0.09
    .CodeAnalysis
    -0.08
    pat
    -0.08
    tees
    -0.08
    loe
    -0.08
    uate
    -0.08
    vé
    -0.08
    à¸ģ
    -0.08
    ов
    -0.07
    داÙĨ
    -0.07
    POSITIVE LOGITS
    ä¸įåı¯æĢĿè®®
    0.09
    äºĭåįĬåĬŁåĢį
    0.09
    身临åħ¶å¢ĥ
    0.09
    å¾·åįİ
    0.09
    缸è¾ħ缸æĪIJ
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    à§ĩ
    0.08
    çļĦ
    0.07
    enge
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    Activations Density 0.016%

    No Known Activations