© 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. 58197
    Prev
    Next
    INDEX
    Explanations

    HTML tags

    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
    Ùĭ
    -0.11
    iewicz
    -0.10
    æĢ§åľ°
    -0.09
    åĦ¿çļĦ
    -0.09
    -0.09
    ently
    -0.08
    ikel
    -0.08
    ãĤĭãģ¨
    -0.08
    ersh
    -0.08
    ellig
    -0.08
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.13
    nya
    0.11
    ä¼ĹæīĢåij¨çŁ¥
    0.11
    äºĭåįĬåĬŁåĢį
    0.10
    åĭĩå¾Ģ缴åīį
    0.10
    ÛĮ
    0.09
    åħ¢åħ¢ä¸ļä¸ļ
    0.09
    åħ¨å¿ĥåħ¨æĦı
    0.09
    俱ä¹IJéĥ¨
    0.09
    Ùĩ
    0.09
    Activations Density 0.060%

    No Known Activations