© 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. 42735
    Prev
    Next
    INDEX
    Explanations

    legal petitioner

    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
    åľ¨
    -0.13
    ed
    -0.12
    缸è¾ħ缸æĪIJ
    -0.11
    åľ¨æĹģè¾¹
    -0.09
    åľ¨èº«
    -0.09
    åľ¨æľª
    -0.08
    åľ¨çľĭåĪ°
    -0.08
    town
    -0.08
    åľ¨å¾Ī大ç¨ĭ度ä¸Ĭ
    -0.08
    åľ¨èĬ±
    -0.08
    POSITIVE LOGITS
    hood
    0.11
    çļĦä¸ĢåĪĩ
    0.10
    ä¹ĭä¸ĢçļĦ
    0.09
    hip
    0.09
    hips
    0.09
    åĢijçļĦ
    0.09
    æľ¬äººçļĦ
    0.09
    /respond
    0.08
    à§įদ
    0.08
    /providers
    0.08
    Activations Density 0.007%

    No Known Activations